Language models can ignore prompt evidence when it conflicts with memorized knowledge. Post-training can make models follow such evidence more reliably, but it is unclear whether these gains require new machinery or strengthen machinery already present. We compare nine post-training arms spanning GRPO, SFT, and DPO from one starting checkpoint, with key comparisons extended across scales and families. We estimate a grounding direction from that checkpoint before training. Across five tested GRPO variants, grounding gains are small. For the two variants replicated across seeds, equivalence tests bound their effects below the conflict-SFT gain even as the rewarded metric improves. Conflict-SFT improves grounding moderately, while DPO drives grounding near ceiling on its matched distribution. Conflict-SFT and DPO largely use the same causal attention-head set as the starting model. Subtracting the starting-model direction suppresses both gains, while adding it to the starting model recovers 35% of DPO's gain at a dose passing all stated side-effect checks. After a supervised warm start makes the context answer appear in more rollouts, the same GRPO recipe adds essentially no further grounding gain. In our setting, grounding gains largely depend on machinery already present in the starting model.
As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive applications. This task is particularly challenging as it requires balancing factual consistency with generation efficiency. Contrastive decoding methods require dual forward passes (with and without context) to compare model outputs, doubling inference computational overhead, while post-training alignment demands extensive reinforcement learning with substantial computational overhead. To address this challenge, we present \textbf{SFAD}, a speculative decoding framework that enhances contextual faithfulness without inference degradation. We first construct \textbf{ConFide}, a preference dataset with fine-grained atomic perturbations, to train a context-faithful draft model via Direct Preference Optimization. During inference, Epistemic Friction detects potential hallucinations by quantifying distributional tension weighted by specialist certainty. When friction exceeds the threshold, Asymmetric Logit Steering refines the target distribution through residual-based logit injection; otherwise, standard speculation proceeds. Extensive experiments demonstrate that SFAD substantially improves faithfulness while achieving $2.48\times$ speedup, offering a practical solution for efficient LLMs.
Large Language Models (LLMs) still exhibit limited capability in following complex instructions. While existing approaches often rely on preference learning to enhance this ability, they typically overlook the relationships between the permissible response spaces of different instructions, which restricts a model to align with subtle and diverse constraint variations. To address this, we propose Cross-Relational Preference Learning (CRPL), a novel framework for constructing preference data that explicitly models inter-instruction relationships through two key techniques: Cross-Relationship Perturbation and Cross-Region Pair Sampling. This enables the generation of more diverse preference data that captures a wide spectrum of constraint variations. Additionally, we introduce an atomic constraint-based verification mechanism to rigorously assess response satisfaction, ensuring high-quality preference pair construction. Extensive experiments across multiple preference learning methods (e.g., DPO, KTO), LLM backbones and four instruction-following benchmarks demonstrate that our approach achieves substantial improvements over prior baselines and exhibits strong generalization.
Positive psychology dialogue aims to support emotional distress and positive resource building, requiring models to produce not only empathetic replies but also coherent progression through a multi-turn support process. Existing resources often reduce supervision to turn-level strategies or holistic preference labels, leaving process position, support function, and local repair targets implicit. We introduce StageWell, a process-aligned Chinese corpus for positive psychology dialogue, together with HQS, a structured protocol for data construction and evaluation. StageWell organizes support into a six-stage support process and uses a multi-agent whole-dialogue rewriting workflow to construct 12,445 SFT instances, 1,849 DPO preference pairs, and a GroundTruth subset of 120 expert-revised dialogues and 977 QA pairs. Guided by HQS, DPO pairs are built as process-localized repairs: flawed model outputs are used as rejected responses, and targeted rewrites under the same context and stage constraint are used as chosen responses. Across four 9B-14B open-source LLMs, this supervision yields robust gains in process control, response quality, and safety. Averaged across models, BERTScore improves by 0.037, Q-Overall increases by 1.32 points, S-exact increases by 0.236, and the H-critical rate decreases by 0.167. These results highlight the value of modeling supportive dialogue as a structured multi-turn support process rather than as single-turn response generation.
Direct Preference Optimization (DPO) aggregates token-level log-probability ratios via uniform summation, implicitly treating all tokens as contributing equally to the preference signal. However, the contribution of individual tokens to the preference signal varies. We introduce token credit, which modulates each token's KL regularization based on its contribution to the preference outcome. We derive that effective token credit is proportional to the magnitude of each token's implicit reward, and observe that this quantity evolves substantially during training. This implies that static token credit becomes increasingly misaligned as training progresses. In this work, we propose Se-DPO (Self-Evolving Token Credit for DPO), a live mechanism that derives token credit from the model's own evolving internal signals during DPO training. Since the reward signal varies in reliability across positions, Se-DPO calibrates token credit based on both the strength and the confidence of each token's contribution. Se-DPO requires no external models, adding only a lightweight calibration network with minimal computational overhead. Experiments show that Se-DPO improves over DPO by up to 9.8 points on AlpacaEval~2 and 12.2 points on Arena-Hard.
Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-resource language alignment, we propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization. By leveraging preference data from other languages, our framework learns a transferable initialization that enables effective adaptation to a target language with minimal data. We provide theoretical guarantees for both the meta-reward modeling and meta-policy optimization settings, and empirically demonstrate the effectiveness of our approach on multilingual benchmarks. In an extremely low-resource setting with only 100 target-language preference samples, our approach achieves up to $28\%$ win-rate improvements over baseline methods, and consistently outperforms baselines across multiple target languages and model scales. Our approaches retain these advantages across different combinations of meta-training languages and varying linguistic distances from the target languages.
Regulated financial institutions operating under data-residency rules need tenant-owned language models that can run inside the institution's perimeter. This paper combines two related FAOS studies into one mechanism-and-control article. First, it reports a reduced-power proof-of-mechanism study of ontology-amplified distillation: a Qwen3.6-27B student is adapted to the Foundation AgenticOS ontology through supervised fine-tuning on frontier-teacher trajectories and ontology-grounded direct preference optimization (DPO), trained locally on a single Apple M5 Max from 47 synthetic, English-language, cross-domain preference pairs. On 40 held-out Vietnamese financial-domain tasks, the distilled student grounds 36 of 40 tasks (grounded rate 0.90; mean ontology term-coverage r_onto = 0.95 on a metric floored at 0.50), equal to the GPT-5 frontier baseline, which also grounds 36 of 40. The outcome is underpowered to establish equivalence: the paired-difference 95% confidence interval spans +/-4 tasks, and the run does not test or show the pre-registered amplification prediction that the student should exceed the frontier. Second, the paper consolidates a contextuality-audit method for enterprise-agent routing. In a separate negative-results pilot, the corrected canonical Contextuality-by-Default degree is zero for all Phase 1.3 groups in both the local-Qwen run and an explicitly labeled Gemma replication check; the useful signal is direct influence and construct coupling, not surviving residual contextuality. Together, the studies pair an ontology-grounded model-building mechanism with a governance diagnostic for deciding when apparent disagreement should trigger prompt standardization, multi-agent synthesis, or human review. The evidence supports neither deployability, safety, superiority, statistical equivalence, nor a contextuality-positive routing rule.
We present Index-1.9B, a series of open small language models developed at Bilibili. The series comprises four models: Index-1.9B-Base, a foundation model with 1.9 billion non-embedding parameters pre-trained on 2.8 trillion predominantly Chinese and English tokens; Index-1.9B-Pure, a control variant trained with an identical recipe but with all instruction-like data strictly filtered from the corpus; Index-1.9B-Chat, aligned from the base model with supervised fine-tuning and direct preference optimization; and Index-1.9B-Character, which augments the chat model with retrieval-augmented generation for few-shot role-playing customization. Pre-training employs a Warmup-Stable-Decay learning-rate schedule in which the concentration of curated data is raised substantially during the decay phase, together with a Norm-Head output layer that stabilizes training under large learning rates. On a suite of standard benchmarks covering examination, reasoning, mathematics, and code, Index-1.9B-Base attains an average score of 64.92, competitive with or exceeding open models of several times its size. We further report controlled studies on model depth, learning-rate magnitude and scheduling, the interaction between learning-rate decay and data quality, and the effect of including instruction data during pre-training, and we document an unexplained surge in benchmark performance midway through the constant-learning-rate phase. All models, together with evaluation code, are released at https://github.com/bilibili/Index-1.9B.
Personalization changes what a model says to a user; we show that it can also change the reasoning trajectory used to justify the response. Modern LLMs personalize interactions by storing user attributes, preferences, and prior context, then injecting this information into future prompts. We study whether such memory reshapes reasoning on open-ended questions where no single ground-truth answer exists. To quantify this effect, we introduce DRIFTLENS, a ground-truth-free framework that maps each expressed reasoning step to a value category and measures divergence between a question's no-memory trajectory and its trajectory under injected user-attribute memory. We first validate that DRIFTLENS distinguishes content-free pragmatic noise from substantive reasoning changes. Across four LLMs and 10 user-attribute categories, including age, occupation, and disability, user-attribute memory induces medium-to-large reasoning drift above each model's pragmatic-noise floor, even when final answers remain fluent, on-topic, and plausible. We then evaluate GRPO- and DPO-based post-training methods for reducing drift. Both reduce drift, but neither uniformly dominates; effects on downstream capability, helpfulness, and instruction following are model-and reward-dependent. These results suggest that memory-induced reasoning drift is a measurable and only partly mitigated failure mode of personalized language models.
To align a Large Language Model (LLM), most existing methods collect explicit human feedback and train a reward model to predict the human preference based on the response text. These existing methods have two key limitations. First, the users rarely provide explicit feedback for LLM responses, which makes the high-quality preference annotation expensive to collect. Second, the methods do not leverage implicit human feedback, which has proven vital to the economic moats of Internet giants. To quantify the value of implicit feedback, we build a new dataset called IFLLM, which collects 1336 multi-turn questions from the 59 Mechanical Turk workers, their mouse trajectories, and eye gazing points to the LLMs' responses from their webcams. IFLLM shows that the users have very diverse types of gazing behavior and mouse trajectories. Our reward model based on the implicit user feedback boosts the accuracy of the text-based reward model from 55% to 64% and nearly triples the relative response quality improvements after applying the DPO to eight LLMs, demonstrating the value of implicit feedback in the wild. Our data collection website, dataset, and codes can be found at https://github.com/themehulpatwari/llm-implicit-feedback/.
Soohyuk Jang, Jiheum Yeom, Nohil Park +4cs.CL cs.AI
Recent Text-to-SQL methods rely heavily on reasoning-centric paradigms such as Chain-of-Thought (CoT), achieving substantial gains on complex benchmarks at the cost of high inference-time overhead. However, a large fraction of real-world queries are simple lookups or aggregations that can be resolved without multi-step deduction, making forced reasoning wasteful. Thus, we propose AutoThinkSQL, a framework that integrates an auto-thinking mechanism into both Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) on Text-to-SQL. Our approach enables the model to dynamically bypass reasoning for simple queries while invoking deep CoT for complex queries. On Qwen3-Coder-30B-A3B, our method achieves consistent gains compared to the best counterpart baseline on both Spider and BIRD benchmarks while simultaneously reducing average output tokens by 24.6% and 18.3%, and average latency by 17.1% and 11.5% compared to CoT-only generation. Further analysis indicates that the model learns to align its reasoning decisions with query difficulty.
Offline preference optimization has become a practical substitute for reinforcement learning from human feedback, but pairwise objectives such as Direct Preference Optimization (DPO) and its variants use only the chosen and rejected responses stored in a static dataset. This leaves a useful signal unused: the response that the reference model itself would generate for the same prompt. We propose Direct Preference Optimization with Penalization (DPOP), a simple extension of DPO that augments the base preference loss with a gated penalty on reference-greedy responses. DPOP activates this penalty only when the current policy still assigns a lower likelihood to the preferred response than to the rejected response. On AlpacaEval 2.0, DPOP improves length-controlled win rate over DPO, SimPO, and AlphaDPO on both Llama-3-8b-it and Gemma-2-9b-it, achieving relative gains of 5.3\% and 4.4\% over baselines on the two models, respectively. Ablations further show that a SimNPO-style length-normalized penalty is stronger than NPO and token-level unlikelihood in this setting.
During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query. While prior work has studied how context characteristics correlate with context usage by the LLM, this analysis has been limited to inference time, leaving open how these relationships are acquired in the first place. Here, we measure how models' sensitivity to such characteristics shifts across successive IFT stages: supervised fine-tuning (SFT), direct preference optimization (DPO), and reinforcement learning with verifiable rewards (RLVR). Experiments across four models and three datasets show that SFT makes models more likely to use contexts that are easy to understand, such as containing high length, context-query similarity, and fluency. Post-SFT dynamics may either reinforce or resolve these preferences depending on the training dataset. Our findings reveal that context usage is actively reshaped at each IFT stage, and designing a balanced IFT dataset is important in ensuring robust context utilization of instruction-tuned models.
Literary translation poses unique challenges due to the scarcity of high-quality annotated data and the need to balance expression fluency with literary effect. We present a multi-aspect iterative refinement framework that generates high-quality translation references and preference data through specialized LLM translators, each targeting a distinct quality dimension. We leverage the generated data for supervised fine-tuning and reinforcement learning. Experiments show that our generated references outperform the original ground truth for SFT by 8.65 CEA100 points. For reinforcement learning, we find that DPO leads to performance degradation in this setting, while leveraging an explicit reward model for GRPO yields an additional 1.51 point improvement. We attribute this to the stability of two-stage training and GRPO's online exploration capability. Our resulting models, LitMT-8B and LitMT-14B, achieve 67.25 and 69.07 CEA100 respectively on the MetaphorTrans English-to-Chinese literary translation benchmark, competitive with Claude Sonnet 4.5 at 68.43, and demonstrate strong generalization to out-of-domain literary work (i.e., O. Henry).
Qiming Bao, Juho Leinonen, Paul Denny +1cs.CL cs.AI
Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness. This blindspot leaves a logical alignment gap -- SFT models reach NLI entailment of only 0.05-0.22 despite producing fluent text. We propose RLearner-LLM with Hybrid-DPO: an automated preference pipeline that fuses a DeBERTa-v3 NLI signal with a verifier LLM score, removing human annotation while overcoming the "alignment tax" of single-signal optimization. Evaluated across five academic domains (Biology, Medicine, Law) with three base architectures (LLaMA-2-13B, Qwen3-8B, Gemma 4 E4B-it), RLearner-LLM yields up to 6x NLI improvement over SFT, with NLI gains in 11 of 15 cells and consistent answer-coverage gains. On Gemma 4 E4B-it (4.5B effective params), Hybrid-DPO lifts NLI in four of five domains (+11.9% to +2.4x) with faster inference across all five, scaling down to compact base models without losing the alignment-tax mitigation. Our Qwen3-8B RLearner-LLM wins 95% of pairwise comparisons against its own SFT baseline; GPT-4o-mini in turn wins 95% against our concise output -- alongside the 69% win the same judge gives a verbose SFT over our DPO model, this replicates verbosity bias on a frontier comparator and motivates logic-aware metrics (NLI, ACR) over LLM-as-a-judge for knowledge-intensive generation.
Preference optimization has become a central paradigm for aligning large language models with human feedback. Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback by directly optimizing pairwise preferences, removing the need for reward modeling and policy optimization. However, recent work shows that DPO exhibits a squeezing effect, where negative gradients applied to rejected responses concentrate probability mass on high-confidence predictions while suppressing alternative responses. This phenomenon arises even in simple softmax models and can lead to systematic probability collapse during training. We introduce Gradient-Gated Preference Optimization (Gate-DPO), a method that stabilizes training by modulating rejected gradients according to the model's probability geometry. When updates target extremely low-probability responses, the gate attenuates harmful gradients while preserving standard optimization behavior. Gate-DPO addresses this optimization pathology without modifying the underlying preference objective and is complementary to existing methods such as extended SFT, IPO, and Cal-DPO. Experiments across multiple architectures and preference datasets show that Gate-DPO consistently reduces squeezing and improves chosen-response likelihood. Mass-dynamics analysis further reveals healthier optimization behavior, with improved preferred responses and reduced suppression of the overall distribution. Notably, smaller gated models can exhibit stronger chosen-response improvements than larger ungated models, suggesting that controlling gradient dynamics, rather than scale alone, is key to stable and efficient alignment.
Preference learning has become the foundation of aligning Large Language Models (LLMs) with human intent. Popular methods, such as Direct Preference Optimization (DPO), minimize surrogate losses as proxies for the intractable pairwise ranking loss. However, we demonstrate that for the equicontinuous hypothesis sets typical of neural networks, these standard surrogates are theoretically inconsistent, yielding vacuous generalization guarantees. To resolve this, we formulate LLM alignment within a margin-shifted ranking framework. We derive rigorous $H$-consistency bounds that depend on enforcing a separation margin $γ$. Crucially, we extend this to Structure-Aware $H$-consistency, introducing a novel objective (SA-DPO) that adapts the margin based on the semantic distance between responses to handle synonyms and hard pairs. Finally, we analyze the trade-off between consistency and model limitations via the Margin-Capacity Profile, proving that heavy-tailed surrogates (such as the Polynomial Hinge family) offer superior consistency guarantees for capacity-bounded models compared to the standard logistic loss used in DPO.