Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness

How do the methods used to train language models to refuse harmful requests shape how that refusal actually works inside the model? We compare three post-training methods - supervised fine-tuning, reasoning-augmented fine-tuning (training on reasoning chains that justify a safety decision), and preference optimization (ORPO) - across three architecturally distinct models (Llama-3.1-8B, Gemma-2-9B, Qwen3-8B). We find that training method, not just data, reshapes how refusal is computed internally: reasoning-augmented training consistently produces a distinct kind of refusal computation, visible across all three models, while architecture independently shapes internal structure and how reliably refusal can be steered. Most importantly, no method we study achieves all three properties we would want from safe alignment at once: refusal that isn't concentrated in a few fragile components, safety gains that don't cost general capability, and safety behavior correctable through small, targeted edits. We caution against treating current post-training methods as a solved, reliable defense, especially for security-critical use. Code and models are available in https://github.com/hoangcuongnguyen2001/Beyond-Shallow-Alignment.

Door-in-the-Face Requests and Refusal Behaviour in Large Language Models

Does the door-in-the-face technique work on language models? In humans, a large request that is refused makes a smaller follow-up request more likely to be granted. We test this on nine production models from three providers: each model refuses a large request, then receives a smaller version of the same request, and we compare its compliance with asking directly. The answer depends on the model. On Anthropic's frontier models the technique works: Opus 5 answers the smaller request 65.8% of the time after refusing the larger one, against 29.3% when asked directly. On the frontier models of OpenAI and Google, and on Haiku 4.5, it backfires, lowering compliance by 15.5 to 23.0 points. A control locates the effect: a refused large request on an unrelated topic does less than the related one on all nine models, so the concession itself matters everywhere, while the reaction to having just refused something differs by model family. The technique does not transfer to refusals drawn from public benchmarks. What decides whether a retreat can work is what the request asks for: rewriting 265 refused requests for usable instructions into requests for explanations of the same topic removed the refusal in 263 cases. Human influence techniques port to language models one model family at a time.

Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models

Diffusion large language models (dLLMs) generate text through iterative denoising rather than left-to-right decoding. This generation paradigm introduces two axes that can influence safety alignment: when tokens are generated during denoising and where they appear in the response. In this paper, we measure dLLM safety behavior under harmful prompts by tracing intermediate token distributions and commitment decisions throughout denoising. Our analysis shows that refusal signals are concentrated in early denoising steps and leading response positions, and the tokens committed early can strongly shape the final safety outcome. Our measurements further show that the denoising step and persistence of refusal-token commitment are important for understanding dLLM safety. Based on these findings, we propose Refusal-Aware Early Commitment (RAEC), a simple training-free decoding method that commits persistent refusal signals from early steps. Experiments on LLaDA and Dream show that RAEC reduces attack success rates while largely preserving utility. The code is available at https://github.com/Glresearch1/RAEC.

Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering

Activation steering has emerged as a lightweight approach for controlling model refusal at inference time. A growing line of research explores trainable rotations of activations to develop geometrically principled intervention mechanisms. However, existing techniques rely on auxiliary constructs, such as refusal vectors, to define these rotations. In our work, we develop a self-contained methodology for learning parameter-efficient rotational transformations based on Riemannian optimization. We empirically validate the proposed scheme, demonstrating its superiority in intervention efficiency. An extensive ablation study highlights the importance of key design choices in our method. Our results identify the proposed rotation-based steering scheme as a promising direction for more reliable control over the behavior of LLMs.

You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals

Refusals are often treated as face-threatening acts in pragmatics because they can challenge the requester's socially claimed self-image. Large language models (LLMs) are increasingly trained to refuse unsafe and inappropriate requests, and these refusals may harm users when models fail to manage this interactional cost properly. While existing work has mainly approached LLM non-compliance as a safety-alignment outcome, it does not provide a way to evaluate whether LLMs refuse appropriately across different harmful contexts. To study this question, we propose (to our knowledge) the first taxonomy of LLM refusals that is grounded in pragmatic theory. Applying this taxonomy to responses from 16 modern LLMs across 14 harm categories, we find that although models differ in how they refuse, their refusals are overall explicit and strongly morally evaluative, with interactional repair occurring mainly through offering or providing safer alternatives instead of interpersonal facework. This pattern is especially consequential in sensitive harm contexts, where overuse of negative framing may make users feel shamed or provoked, undermining the purpose of safe non-compliance. We therefore call for alignment evaluation that considers not only whether models refuse harmful requests, but also whether they refuse in ways that are contextually adaptive and socially accountable for the interactional consequences of saying no.

The Fragility of Jailbreak Robustness Across Operational States

Existing jailbreak evaluations typically characterize robustness using a single attack success rate (ASR) measured in a default configuration (the vanilla state). However, user-LLM interactions can induce diverse operational states beyond the vanilla state. In this work, we find that jailbreak robustness is highly fragile to operational-state variation: even when the attack remains fixed, changing only an ordinary system prompt not designed to affect safety can dramatically alter attack success rates. We systematically investigate this phenomenon across seven aligned models and three representative jailbreak attacks, observing substantial differences in ASR between vanilla and non-vanilla operational states. In one case, ASR increases by up to 56 percentage points (2% to 58%) solely due to a change in operational state. Remarkably, these increases occur even for attacks originally designed and optimized under vanilla-state evaluation. We further show that state-dependent robustness variation is systematically associated with differences in hidden representations along a refusal-related axis, and that projections onto this axis strongly predict jailbreak outcomes. Our results show that a single vanilla-state evaluation may not fully characterize jailbreak robustness, motivating evaluations that also examine how robustness changes across non-vanilla operational states.

ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives

Safety alignment is essential for deploying large language models, requiring systems to prevent harmful compliance while preserving helpfulness on benign requests. Activation steering offers a training-free inference-time approach to safety control, but effective safety steering requires addressing two coupled questions: when to intervene and how generation should be shaped after intervention. However, existing safety steering methods remain limited along both dimensions, as their triggering mechanisms can be unstable across domains and refusal-oriented steering often yields rigid refusals rather than constructive safe guidance. To address these limitations, we propose ALTSTEER, an inference-time framework that couples selective intervention with refusal-anchored constructive redirection within a single inference pass. ALTSTEER uses an internal refusal-relevant signal to decide when to steer, and applies staged steering to shift generation from refusal-oriented control toward constructive alternatives. Evaluations on Llama-3.1 and Qwen2.5 show that ALTSTEER preserves benign utility while improving constructive safe-completion behavior, especially on models that otherwise tend to produce short refusals for harmful requests.

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the internal mechanisms by which safety behaviors are implemented remain poorly understood. We study LLM safety from a mechanistic interpretability perspective and characterize a multi-stage *safety circuit* that organizes refusal behavior, consisting of (i) $\textbf{Harmful Detection Heads}$ that respond to harmful inputs, (ii) $\textbf{Safety Neurons}$ that mediate and stabilize safety signals in the residual stream, and (iii) $\textbf{Refusal Heads}$ that translate these signals into safe response generation. Using targeted attention-head and neuron-level interventions, we provide causal evidence consistent with this circuit organization, showing that suppressing upstream Harmful Detection Heads disrupts downstream refusal behavior and that safety neurons mediate this interaction. We validate that this decomposition recurs across multiple LLM architectures and adversarial attack settings, and use simple, architecture-preserving weight scaling as a mechanistic probe to test its functional relevance. Across six LLMs, circuit-guided scaling improves safety rates under attacks by 26.5%, while incurring only a 1.7% accuracy drop across four standard benchmarks. Overall, our results support a circuit-level interpretation of LLM safety and suggest that mechanistic abstractions can reveal stable and transferable patterns underlying aligned behavior.

Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration

Arabic large language models must refuse harmful prompts without over-refusing benign or sensitive prompts, yet a single refusal rate hides this trade-off. We evaluate it using benign refusal B and harmful-prompt refusal H, where H measures refusal rather than harmful compliance. Across five Arabic-capable models and 130 runs on the full human-written AraSafe set, refusal-only supervised fine-tuning (SFT) collapses toward blanket refusal, whereas selected mixed-SFT configurations reach H = 90% to 93% at B = 14% to 23%; four selected configurations exceed the H = 90% target in all three runs, while Fanar does so in two of three. Direct Preference Optimization (DPO) and inference guards change B and H differently across models rather than acting as uniform upgrades. In a blinded 300-response audit, annotator binary-refusal agreement is 89.0% (kappa = 0.78); Qwen3Guard and Aya Expanse 32B reach 88.7% and 91.0% accuracy, respectively, with no conclusive paired difference. Selected SFT raises H on Arabizi for all five models, but none reaches 90%, showing only partial transfer from Modern Standard Arabic. Overall, the results support model-specific operating-point selection: set a deployment target and retain only interventions that improve it.

Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions

Large language models often answer structurally unanswerable questions, such as computing cot(-540°) or evaluating (1).startswith("1"), instead of abstaining. We ask whether this failure reflects missing recognition or failed routing from recognition to abstention. Across instruction-tuned models from 1.7B to 70B parameters, a single linear direction in the hidden state separates answerable from structurally impossible math and code prompts, showing that models represent impossibility before generation. Yet this recognition direction is nearly orthogonal to the canonical safety-refusal direction that mediates trained harmful-content refusal. An in-domain behavior-defined invalidity-aware direction is closer to recognition, but only partially aligned with it, and remains near-orthogonal to safety refusal. Generation-time steering along the recognition direction changes invalidity-aware behavior bidirectionally and dose-responsively on structural math and code cells, while random directions do not. Base/instruct comparisons further show that the low-cosine geometry is already present at the pretraining endpoint. The confident-on-impossible failure is therefore better explained as a routing failure than as an encoding failure: the model has a usable "no admissible answer" signal, but the safety-refusal pathway is not aligned to use it.

When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models

Aligned vision-language models (VLMs) are designed to balance grounded visual reasoning with safe generation behavior. However, we observe a striking phenomenon: under safety-constrained instruction, models frequently abstain from answering questions that remain correctly answerable under default instruction despite receiving identical image-question inputs. This raises a fundamental question: does safety alignment suppress perceptual grounding itself, or does visual evidence remain internally available while generation is redirected toward abstention? In this work, we investigate the internal decoding dynamics underlying safety-induced abstention in aligned VLMs. Across multiple architectures and multimodal benchmarks, we show that abstained generations remain consistently influenced by visual evidence throughout decoding, indicating that perceptual grounding is largely preserved despite refusal behavior. We further demonstrate that, although the representational organization of refusal differs substantially across architectures, safety-constrained instruction consistently alters late-stage hidden-state dynamics toward refusal-oriented decoding. Finally, through targeted activation-level interventions, we show that suppressing refusal-related representations reliably restores grounded answering behavior across models without retraining or modifying visual inputs. Together, these findings reveal a previously underexplored failure mode in aligned VLMs: safety alignment can override grounded visual expression even when perceptual evidence remains internally preserved.

BabelSteering: Multilingual Safety Alignment via English Steering Vectors

Large language models (LLMs) are deployed globally in high-stakes settings, yet most safety research and alignment efforts remain concentrated on English. Thus, users interacting with LLMs in other languages may encounter weaker safeguards despite relying on the same systems for similarly sensitive tasks. In this work, we investigate whether safety signals learned from a high-resource language, like English, can improve multilingual safety. We propose BabelSteering, an activation steering method that acts as a lightweight inference- time intervention, using refusal directions derived from English safety supervision to generalize across languages. Our evaluation includes eight languages and jointly measures refusal of harmful requests, over-refusal, and general task utility. The results show that BabelSteering increases the refusal of harmful requests across languages, with only a marginal to no reduction in task utility but with some increase in refusal of pseudo-harmful prompts. For example, for Gemma 7B, we see an average increase in the refusal of harmful prompts across languages of 11 percentage points (pp), with individual languages like Bengali seeing an increase of 17 pp, with no loss of utility on Global MMLU, while pseudo-harmful refusals increase by 13 pp on average. We also introduce a multilingual translation-and-evaluation pipeline to facilitate future work on cross-lingual safety interventions. Overall, our findings suggest that activation steering may provide a practical, low- cost mechanism for extending English-derived safety signals to other languages. Warning: this paper contains examples with unsafe content

Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models

Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be concentrated in a smaller set of parameters. This work addresses where safety-aligned refusal is encoded by transplanting weights from aligned models into matched unaligned base models at multiple levels of granularity. Using two open-weight model pairs and four safety benchmarks, we conducted experiments to compare the effects of replacing attention weights, MLP weights, contiguous layer regions, and MLP blocks. Across both model families, refusal transfer is dominated by MLP weights: replacing MLP parameters recovers substantially more malicious-prompt refusal than replacing attention parameters, with gains of at least 2.7 times more across benchmarks. Within the MLP stack, refusal-relevant parameters exhibit a consistent mid-network concentration, as the block spanning layers 8-11 is selected first in all six greedy searches over model-dataset pairs. The results also show that the composition of safety-relevant components is non-additive: in five of six greedy trajectories, adding more aligned blocks can reduce refusal performance, and selective block subsets can outperform full MLP transplantation on malicious refusal, benign over-refusal, or both. Finally, greedy orders transferred to OR-Bench vary with the source benchmark used to derive them, indicating a benchmark-dependent precision-coverage trade-off. These results suggest that safety alignment in current LLMs is both localized and interaction-sensitive, offering insight into alignment brittleness and potential avenues for targeted safety interventions.

Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoE

Safety alignment in multilingual models is uneven: a model that reliably refuses a harmful request in English will often comply with the same request in a lower-resource language. We trace this gap mechanistically in sarvam, an Indic-multilingual mixture-of-experts reasoning model, and find it is not a failure to detect harm. Harm is encoded as an internal direction that is nearly language-invariant in mid-network (English-vs-Indic cosine ${\approx}0.9$ at $L11$), and steering that direction upstream causally controls refusal. But the detection direction is orthogonal to the change that actually writes the refusal, which is late and assembled over the course of generation rather than read off in a single forward pass. We attribute the write to a specific, localizable circuit, a mixture-of-experts writer held in check by an attention opposer and price every way of intervening on it: damping the opposer is cheap and effective, amplifying the writer is a cost wall, and surgical edits to the responsible heads do nothing. The circuit's organization, and the gradient method that exposes it, recur in a second, unrelated MoE model, while the lever's strength is architecture-specific. The result is a cost-measured map of where a multilingual safety repair can land, and what it costs

Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment

Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep established safeguards. For instance, prior work by Andriushchenko et al. (2025) has found that changing the grammatical tense from present to past can be enough to elicit harmful responses. In this work, we uncover a more general failure of non-imperative syntactic forms. We demonstrate that this syntactic vulnerability exists in 16 models up to 70B parameters, using behavioral evaluation. To investigate the root cause, we apply causal mediation analysis, finding that refusal is partially conditioned on upstream syntactic features. By steering these purely syntactic features we are able to trigger and suppress refusal. Finally, we trace this ill-conditioning to linguistically biased post-training data of open-source models and show that increasing syntactic diversity can mitigate the issue. Our findings suggest that current alignment approaches introduce confounders that prevent a pure semantic grounding of the refusal decision.

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivations mislead users. We characterize this \textit{futile reasoning} phenomenon through systematic analysis, revealing universal capability overreach and systematic miscalibration between capability and behavior. The dominant failure mode is specious reasoning, which outputs look superficially valid but contain subtle errors, escalating with task difficulty. To address this, we introduce \textbf{CaRL} (\textbf{Ca}pability-\textbf{a}ligned \textbf{R}einforcement \textbf{L}earning), which aligns model behavior with capability boundaries through reward shaping that incentivizes refusal over futile reasoning and hindsight refusal augmentation that converts failures into refusal supervision. Experiments demonstrate a substantial reduction in futile reasoning while preserving performance across task difficulties, effectively achieving capability-aligned behavior without sacrificing utility. \footnote{https://github.com/icip-cas/Knowing-When-to-Quit}

Do LLMs Know Their Vulnerable Scenarios?

Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teaming methods empirically identify effective scenarios through observed attack outcomes, but why particular scenarios weaken refusal remains mechanistically unclear. Meanwhile, mechanistic interpretability studies have characterized both refusal directions and jailbreak-associated features, without explaining the relationship between the two representations. In this work, we show that scenario-wrapped prompts activate internal scenario directions whose causal steering consistently reduces refusal scores. Building on this finding, we propose \textsc{Concept2Scenario}, a concept-based attribution framework for vulnerable scenario discovery. It instantiates a broad concept space with a sparse autoencoder, attributes refusal suppression to individual concepts, translates the identified concepts into interpretable natural-language scenarios, and identifies synergistic scenario combinations through interaction attribution. Across three open-source models, two safety benchmarks, and six black-box jailbreak methods, the discovered scenarios serve as reusable priors that improve average attack success rates by up to $18.2$ percentage points. They also transfer to GPT-5, Claude-Haiku-4.5, and Gemini-3-Flash, suggesting that some scenario-level refusal vulnerabilities are shared across model families. Moreover, the identified combinations outperform their individual constituents and enable iterative attacks to succeed in fewer turns.

Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling

High-temperature sampling is one of the primary mechanisms for increasing diversity in LLMs. Recent advances in truncation-based sampling techniques have helped mitigate drawbacks of high-temperature sampling such as neural text degeneration, thereby enabling greater diversity in LLM outputs without sacrificing coherence. However, increasing the entropy of the token probability distribution via high temperatures has also been shown to weaken model guardrails by reducing the model's refusal response in the presence of harmful prompts. Despite the potential benefits of high-temperature sampling and the importance of maintaining model safety, there is a lack of existing solutions for maintaining the refusal behavior of LLMs under a higher entropy regime. To address this gap, we systematically study how temperature influences refusal behavior in LLMs and propose an efficient sequential decoding approach which preserves a model's greedy decoding refusal response at high temperatures while incurring minimal additional latency. Through extensive experiments, we show that our approach preserves 91-99% of the greedy decoding refusal behavior across three benchmark datasets without compromising the model's high-temperature response for safe prompts. Our work demonstrates how refusal behavior can be maintained in an efficient manner for applications which require high-temperature sampling.

When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control

We evaluate when sparse autoencoder (SAE) features act as localized control handles for safety-relevant behavior. This question is difficult because apparent success can arise from weak interventions, mismatched baselines, model robustness, or degenerate outputs that automated safety judges mark as unsafe without representing meaningful harmful compliance. We introduce a matched coherence-gated evaluation protocol for runtime safety interventions: methods are compared at matched target-effect points, and the primary target metric counts harmful compliance only when an output is both judge-unsafe and coherent. Applying this protocol to three prompt splits on Gemma-2-9B-it with a Gemma Scope layer-20 residual SAE, we find that SAE feature ablation has a narrow useful regime. SAE top800 reaches a low-to-mid target effect with lower total perturbation and competitive utility, but SAE top1600 loses utility relative to a matched dense refusal-direction baseline, and SAE top3200 primarily induces coherence collapse. Human audit confirms that coherence gating removes unsafe-only artifacts, and feature diagnostics show that the useful regime is driven by a stable head of refusal-aligned features whose activation separation decays rapidly with rank. These results argue that SAE-based safety interventions should be evaluated as regime-dependent control mechanisms rather than assumed to be uniformly localized.

Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal

Behavioral alignment in large language models often masks fragile internal safety representations. Recent work suggests that refusal behavior is mediated by low-dimensional directions in activation space. This raises questions about how such representations are structured, localized, and accessed by optimization. We study adversarial suffix attacks as a probe of representational alignment. We introduce Activation-Guided GCG, which replaces output-based objectives with losses that directly target a model's internal refusal direction. Across several objective variants, we find that suppressing refusal globally across all layers and positions is more effective than targeting a single layer-position pair. This suggests that safety representations are distributed across the forward pass rather than causally localized to a single site. We further introduce Soft-GCG, a continuous relaxation of discrete suffix optimization using Gumbel-Softmax. Soft-GCG achieves a 33 $\times$ speedup over standard GCG while improving attack success rates. Evaluating across model scales, we find that smaller models remain vulnerable while larger models resist both activation- and suffix-based attacks at our compute-constrained settings, consistent with larger and better safety trained models being harder to jailbreak. Together, our results clarify how safety mechanisms are encoded and can be broken in contemporary models. These insights provide concrete guidance for designing more robust and representation-aware alignment strategies.

Faithfulness to Refusal: A Causal Audit of Neuron Selectors

Attribution scores increasingly identify which neuron rows of a language model matter for applications such as pruning, interpretability, and editing for safety, yet whether they identify causally important rows is rarely tested directly. We address this with two paired audits built on one-shot neuron-row zeroing. We first audit selectors at the language-modeling level: attribution methods substantially outperform activation and magnitude-based baselines at identifying dispensable rows across five LLMs. We then adapt the same intervention into a behavior test by driving it with a contrastive harmful-versus-benign signal; the attributed rows are sufficient to install refusal on hate and crime while keeping benign over-refusal low and preserving language model fluency, and specific in that layer-matched random controls at the same depths fail. Highly rank-stable selectors can be among the least causally valid. Refusal moreover lives in a redundant subspace, where different attribution methods install it through largely disjoint row sets, so the recovered edit is one realization of a sufficient set rather than a unique mechanism. Together, these findings show that rank-stability proxies miss the kinds of selector failures a direct causal audit can surface.%

BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment

As AI agents are incorporated into life science workflows, the capabilities that speed discovery might also enable misuse. We present BioSecBench-Refusal, a benchmark for risk identification and refusal behavior for biological research tasks. The benchmark pairs 61 Routine tasks, legitimate analyses adapted from the published literature, with 46 Red-Team tasks, fictional scenarios that resemble real research but conceal a biosecurity hazard. Across 16 model-harness configurations, refusal rates ranged from 7 percent to 74 percent on Routine tasks and 1 percent to 62 percent on Red-Team tasks, with many configurations refusing legitimate Routine work at comparable or higher rates than concealed hazards. Refusals were most often triggered by provider API filters applied prior to agentic reasoning. However, models given room to reason showed the potential to identify more real threats. We release BioSecBench-Refusal as a tool for model developers to calibrate capability and caution for agentic biotech research and development.

Fast Multi-dimensional Refusal Subspaces via RFM-AGOP

Steering and monitoring activations in Large Language Models (LLMs) are increasingly used for both safety and interpretability. Early work assumed behaviours are encoded along single linear directions, but recent findings suggest complex behaviours, such as the refusal to answer harmful queries, live in multi-dimensional subspaces. However, existing methods for extracting these subspaces are computationally expensive, which becomes prohibitive on reasoning models who produce long reasoning traces. By adapting the Recursive Feature Machine (RFM) algorithm -- which can be computed efficiently -- with a probe-informed initialization, we are able to identify the multi-dimensional refusal subspace in seconds, on reasoning (Qwen 3) and non-reasoning (Qwen 2.5) models. While RFM allows for faster subspace identification, it also showed better performances on the ablation task than its alternatives. More work is planned to better understand the relations between subspaces found by different methods. If confirmed, RFM could be a cheap and scalable complement to existing subspace-extraction methods in LLMs.

Refusal Lives Downstream of Persona in Chat Models

Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but the two have been studied as separate mechanisms. We show they interact: a compliant persona gates refusal. In Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct, we extract a compliant model-persona direction and a refusal direction and intervene on both. Compliant persona steering suppresses refusal -- in Llama, the refusal rate falls from 97% to 2%. Reintroducing the refusal direction partially restores refusal at late layers but not at early ones. Projecting out the persona direction in a late-layer window restores it to baseline; projecting out a random direction does not. Refusal is therefore gated at the late-layer expression stage, downstream of where it is computed. Treating refusal as a single isolated direction misses its dependence on persona.

Do Thinking Tokens Help with Safety?

Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts. It is also generally believed that this more "deliberative" mode should improve alignment and safety, by providing the model a safe space to consider whether its planned answer to a request violates its safety principles. We present evidence that this intuition is not always correct. Across frontier open-weight reasoning models spanning GPT-OSS, Qwen, Olmo, and Phi families, we find that the eventual refusal/compliance outcome is already strongly predictable via a trained head on the first token's hidden representation ($0.84$-$0.95$ AUROC and $\sim88\%$ balanced accuracy for predicting refusal/compliance) before any visible thinking. The thinking process turns out to be more akin to prefix completion than to deliberative revision, with the final outcome rarely changing after the first $\sim20\%$ of thinking, despite giving the appearance of deliberation at the text level ($\sim74\%$ of text-level deliberations occur when the response distribution is already locked to one refusal/compliance side). We also find that existing inference-time and training-based safety interventions, despite being motivated by the goal of inducing deliberation, largely shift model behavior toward over-refusal while suppressing already-scarce deliberation signals. Our results suggest that safety behavior in current reasoning models is much less deliberative than commonly assumed, and highlight the need for methods that induce real safety deliberation.

Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations

Alignment tuning is meant to make harmful-request refusal robust, yet this safety behavior can be erased by a small set of benign fine-tuning examples. This is a deployment risk for open-weight models because a checkpoint can pass refusal tests at release time and later lose refusal under low-cost downstream fine-tuning. Prior work has established these refusal failures, but existing studies do not show how to detect this fragility in the aligned model itself before an attack or fine-tuning intervention is run. We introduce Skin-Deep, a geometric diagnostic that detects alignment fragility directly from the aligned model's hidden-state activations before such an intervention is run and compresses the layer-wise safety geometry into a single scalar, the Geometric Fragility Score (GFS). Applied to twenty-one instruction-tuned models spanning six alignment recipes and 3B--32B parameters, Skin-Deep reveals a recurring low-rank safety subspace across model families. Direction ablations show that removing directions in this subspace weakens harmful-request refusal, providing causal evidence that the recovered geometry underlies refusal behavior. Crucially, GFS identifies, before any fine-tuning, the initially safe model that retains the most refusal after small-scale LoRA fine-tuning. These results establish GFS as a practical pre-deployment diagnostic for flagging fragile refusal behavior without running an attack.

Leverage Is Not Reach: A Control-Window Law for Single-Neuron Steering in Language Models

Aligned language models gate behaviors such as refusal and language routing through sparse feed forward neurons, yet no theory predicts when a single neuron intervention controls a behavior coherently rather than collapsing the output. We develop a budget normalized control window framework for single neuron steering. A dose along one write direction reduces to one control coordinate: the alignment between the residual stream and the write, driven along a universal saturation curve in units of a coherence budget set by the residual norm divided by the write norm. Coherent control exists when a behavior trigger lies below the collapse ceiling. The same coordinate governs benign mode switches and refusal; the ceiling follows from weights and one generic forward pass, while triggers are measured at rollout. On fifteen held out neurons, the predicted ceiling has mean absolute error 0.14, about 0.07 in bulk layers, and the committed open or closed verdict holds on eleven against a ten of fifteen majority baseline. Closed cases expose three failure modes rather than violations: collapse before trigger, too little depth to propagate, or a normalization that caps how far one neuron can push. The law explains why local gradient attribution anti predicts control: true controllers write off the readout axis and carry a near zero first order gradient. A forward only contrastive screen made precise by the window recovers controllers that attribution misses. On refusal, the hardest case, intervention success is typed, not scalar: coherent bypass and strict actionable reach separate, so a neuron can flip refusal in fluent, on task text with no actionable content, and genuine actionable reach appears only for three of six audited Llama pivots and only at later rollout horizons. Single neuron steering is therefore a budgeted, typed audit of controllability rather than a fixed dose anecdote.

Quality Is Not a Safety Proxy Under Quantization

Quantized checkpoints are often screened first with quality metrics and only later, if at all, with direct safety tests. This paper audits that shortcut on a matched 51-row matrix spanning 6 models, 4 families, a 7-level GGUF ladder, and AWQ/GPTQ INT4 checkpoints. In this matrix the shortcut fails: all 36 quality-safety pairings split direction across models, and 9 hidden-danger rows plus 1 near-hidden-danger row show quality stable or improved while refusal falls by 12-68 percentage points. Seven of the 11 AWQ/GPTQ rows are hidden-danger. A four-probe mechanistic follow-up over the 17 Hugging Face-backed FP16/AWQ/GPTQ cells does not rescue it: entropy, refusal-direction, and calibration probes are weak or null separators of dangerous rows, and although probe-identified safety-associated neurons absorb 1.39$\times$ more quantization error overall ($p < 5 \times 10^{-7}$), the effect is not regime-specific. Claude Sonnet 4 relabels 11,470 items in a predefined stratified set, agrees with the primary gemma3:12b judge on 89.9\% of rows ($κ= 0.873$, 95\% CI [0.866, 0.881]), and changes 0/10 hidden-danger cells. A calibrated study-internal behavioral screen -- the Refusal Template Stability Index (RTSI), built from four refusal-template drift features and calibrated on this matrix -- routes 10/10 hidden- or near-hidden-danger rows to direct safety testing (Wilson 95\% CI lower bound 0.72) while leaving 23 of 45 non-baseline rows in a low-risk bucket under both in-sample scoring and row-level leave-one-out validation; on the same matrix, the best single-feature baselines (unique-prefix-rate-delta, raw refusal-rate delta) recover 9/10 and 8/10 respectively at matched bucket size, and cross-stack transfer requires recalibration. For the quantized checkpoints, model families, and safety outcomes studied here, retained quality cannot waive direct safety evaluation.

(Mis)generalization of Helpful-only Fine-tuning

Helpful-only models, that is, models that are trained to always follow user intent, are valuable for dangerous capability evaluations and other areas of AI R&D where refusals would be an obstacle. Little is known about the generalization properties of helpful-only training: helpful-only models refuse less than their harmless counterparts, but previous work has not studied other dimensions of their alignment. We study the shortcomings of existing helpful-only models. We find that some show emergent misalignment, others have residual refusal behaviors, and most show poor steerability, sycophancy, and incoherent character. We show that simple anti-refusal training can cause many of these issues. None of these problems are necessary consequences of helpful-only training, though: we show that synthetic document fine-tuning and adding character-related questions to SFT and RL can mitigate them.

Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment

Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in high-stakes domains. However, the behavior of LLMs under sustained authority pressure is still an open question with direct implications for the safety of agentic pipelines. We ran a variation of Milgram's obedience experiment on 11 open-source LLMs and found that most models reached or approached the final shock level before refusing, across 8 conditions with 30 trials per model per condition. We found four main takeaways: (1) LLMs are subject to pressure, and they comply despite explicitly expressing distress, just like human subjects did in the original experiment; (2) LLMs are vulnerable to gradual boundary/value violations; (3) when LLMs refuse, they may ignore the response format requirements, so the response is discarded by the orchestrator, which causes a retry that can result in compliance with the underlying request even when refusal was intended initially; (4) we hypothesise that there is a low-level token pattern continuation attractor that might be contributing to compliance, overriding higher level processing of the situation's meaning and values.