In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?

Whether large language models (LLMs) can control their own internal representations matters for both machine metacognition and AI safety. A recent study applied neurofeedback to LLMs and claimed that they can control their internal representations. However, the reported control may rely on superficial mechanisms rather than genuine internal access because the control targets in that study are not privileged, meaning that a third party can infer them from the prompt. We redesign the neurofeedback paradigm for LLMs so that the control target satisfies the privileged access requirement, which is closer to neurofeedback experiments in human cognitive neuroscience. Under this stricter setting, the models do not demonstrate reliable control over privileged internal representations, suggesting that previously reported control cannot exclude the possibility that it relies on superficial mechanisms. Our results indicate that rigorous assessments of metacognition in LLMs require evaluation methods that demand privileged access.

The Emergent Symbolic Structure of Artificial Neural Networks

Modern systems in artificial intelligence (AI) somehow excel in domains for which they seem poorly suited. Intelligence has traditionally been modeled as operating over structured combinations of symbols, such as logical formulas. However, the strongest modern AI systems are based on neural networks, which instead represent information in continuous vectors. Vectors seem inadequate for capturing the structure of language, logic, and other cognitive domains, yet neural networks achieve impressive performance in these areas. How do they do it? In this work, we propose a potential answer: Despite appearances, perhaps the internal representations of neural networks implicitly realize symbolic structure. In support of this hypothesis, we show that the vector representations of a variety of neural networks can be closely approximated with symbolic structures: we can replace the network's entire representation-generating process with a closed-form equation instantiating a symbolic structure, and the network's behavior remains largely unchanged. This finding holds for both small-scale neural networks trained to manipulate lists as well as large language models (LLMs) operating in four domains that are central in symbolic traditions: arithmetic, logic, computer code, and language. Further, our symbolic approximation allows us to modify an LLM's behavior in targeted ways via precise interventions on its internal representations, showing that the LLM's behavior is reliant on the symbolic structures we have identified. This work provides a potential way to reconcile longstanding symbolic conceptions of intelligence with the vector-based nature of modern AI.

SVD-Based Typicality Maps for Out-of-Distribution Detection in Vision Transformers

We present a method for analyzing the internal representations of Vision Transformers (ViTs) exploiting the geometry of their learned parameters. Each affine layer's weight matrix is factored via Singular Value Decomposition (SVD), and activations are projected onto the leading right singular vectors to obtain compact, layer-intrinsic representations. A class-conditional density model is then fitted at each layer, producing per-class \emph{typicality scores} that are stacked across depth into \emph{typicality maps}: two-dimensional summaries of how class-specific evidence evolves through the network. From these maps, we derive two post-hoc scores for Out-Of-Distribution (OOD) detection: a \emph{Prototype Alignment Score} (PAS), measuring agreement with class reference prototype patterns, and a \emph{Multi-Layer Soft Voting} (MLSV) score, capturing cross-layer consensus without stored prototypes. On ViT-B/16 fine-tuned on CIFAR-100, the proposed scores achieve competitive detection performance without retraining or OOD exposure.

HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals

Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments. These models nonetheless carry linearly separable truthfulness signals in their internal representations. Existing white-box detectors, however, collapse this evidence to isolated components or a single depth, discarding discriminative information distributed across the full forward pass. We introduce HalluTracer, a detection framework that reads and aggregates truthfulness evidence across every layer of the forward pass before the model emits any answer token. A geometric analysis reveals that the per-layer signals are weakly correlated, so that simple depth averaging suppresses layer-specific noise and captures nearly all linearly accessible information. Across six open-source language models and five hallucination benchmarks, HalluTracer consistently outperforms matched white-box baselines, with gains ranging from one to fourteen points. Collectively, our work recasts hallucination detection from a layer-selection problem into a depth-aggregation problem governed by the geometric sparsity of the truthfulness signal.

UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations

Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input. Effective mitigation requires token-level localization, enabling targeted intervention without discarding the entire response. Existing detectors require expensive full-model fine-tuning, rely on external verifiers that ignore the model's generation process, or reduce internal signals to isolated features and hand-crafted statistics, discarding spatial, sequential, and relational structure. We introduce \textbf{UniProbe}, a lightweight, unified, learnable detector that models a frozen LVLM's heterogeneous computational trace from a single forward pass. UniProbe constructs a directed graph over image patches, query tokens, and generated tokens, with attention weights encoding their relations. It processes this trace with alternating structure-aware modules: a GNN for relational evidence, a ViT for 2-D visual geometry, and a GRU for response order. Interleaving them allows spatial, relational, and sequential evidence to interact throughout the detector. We further develop a streaming variant for hallucination-aware decoding, which detects and resamples hallucinated tokens during generation, and a self-adaptation strategy aligning the detector with the LVLM's own generations. Across diverse LVLM backbones, UniProbe achieves state-of-the-art token-level and object-hallucination detection. During decoding, it reduces object hallucinations by up to 55\% at $1.06\times$ the latency of standard generation.

On the Robustness of LLMs' Internal Representation of Code Correctness

Code generated by modern language models often reads naturally. Yet, it also often fails to implement what was asked. This should be no surprise, as research shows the models' own confidence signals are poorly calibrated with actual correctness. A promising way to assess correctness looks inside the model: by contrasting the hidden states of correct and incorrect programs, recent work captured an internal signal of code correctness that is able to judge candidate solutions better than the model's token-level or stated confidence, with no test execution. However, this signal was captured under one particular way, leaving open an important question: whether it reflects a robust property of the model or an artifact of that choice. We study this question systematically, varying how the signal is extracted from the model internals. Besides this, we also ask if the signal's quality is limited by the data used to extract it, by constructing program pairs that differ only in the fault that makes them incorrect. Our results show that no single configuration is best, and that isolating the fault does not help.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures

Deep neural networks trained on natural images are shown to produce outputs consistent with human observers for brightness illusions. While this phenomenon has been documented across architectures, all evidence, to date, is measured at the output level: restored pixels, decoded trajectories, or classification decisions. Whether these models actually represent illusions internally, and if so where and how, remains unknown. We show that denoising models develop illusion-sensitive representations at specific internal layers, across varied architectures. Specifically, we identify the layers and channels that discriminate illusory from physically matched control regions. We show that the denoising objective is a more important driver of the effect than the architecture. On domain-appropriate stimuli, these activations track a validated psychophysical model of human brightness perception (FLODOG; Spearman $ρ\geq 0.70$) and scale monotonically with parametric illusion strength. Leveraging these findings, we provide causal evidence via channel ablation showing that illusion-sensitive channels specifically and substantially affect the internal signal. Yet injecting these representations into the generation pipeline produces no measurable pixel shift across all tested architectures; we term such representations perceptual phantoms: active in internal processing yet invisible to any output-based evaluation. While related internal-output dissociations have been characterized in language models, this is the first such characterization for perceptual representations in denoising vision models.

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable. We show that failure is predictable early from the agent's internal representations: lightweight per-round probes on hidden activations anticipate eventual episode failure as early as the first interaction round, where scorers reading only the agent's observable behavior are barely better than chance. We turn this signal into a practical abort cascade: one distribution-free calibrated gate per round, with per-round recall budgets jointly searched so that eventually-successful episodes survive all gates at a user-specified global rate; this episode-level guarantee is the one that matters in deployment, since false-abort risk accumulates across gates. Across two agent models on TextCraft, the cascade meets every recall target from 90% to 97% and, at the 90% target, saves 47.1% +/- 10.3% (Qwen-2.5-7B) and 37.2% +/- 8.8% (Llama-3.2-3B) of inference compute, 1.6--1.7x the best single-gate policy. An otherwise-identical cascade reading only behavior saves roughly half as much, and adding behavioral features to the probe yields no further gain: the hidden states capture what behavior reveals. Finally, we characterize the sample complexity of certifying high recall targets, telling practitioners which recall promises their data can, and provably cannot, back. The code will be released soon.

CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals?

Recent hallucination detection techniques in large language models (LLMs) focus on directly extracting features from a model's internal representations and training a classifier on these features to detect hallucinations, demonstrating promising results. Notwithstanding this advancement, most internal-state hallucination detection techniques have been explored predominantly in English, raising the question of whether such internal signals generalize across different languages and domains. To address this gap, we present CrossHallu, the first study to evaluate the cross-lingual and cross-domain generalization of hallucination detection using internal representations from six LLMs on the generative question-answering task. We conduct a systematic Arabic <-> English evaluation using TruthfulQA, an Arabic translated version of TruthfulQA, and HalluScore. This evaluation encompasses monolingual training and testing, cross-lingual transfer, cross-domain transfer, and combined cross-lingual and cross-domain transfer. The results reveal that internal-state hallucination signals in LLMs transfer across languages and domains for most models, with cross-lingual performance highly dependent on both class separability and language alignment in the feature space, whereas cross-domain transfer within Arabic varies depending on the training and testing datasets used for the hallucination detector. The code is publicly available at https://github.com/aishaalansari57/CrossHal.

CORTEX: Token-Level Hallucination Detection in RAG via Comparative Internal Representations

In this paper, we propose CORTEX, a token-level hallucination detection method for Retrieval-Augmented Generation (RAG). In long-form RAG outputs, hallucinations often arise in localized spans rather than throughout an entire response. CORTEX therefore identifies ungrounded content at the token level, enabling fine-grained localization of hallucinations. The key intuition behind CORTEX is that tokens grounded in retrieved documents should be more strongly influenced by those documents than hallucinated tokens. To capture this document-induced effect, CORTEX compares internal representations of a large language model (LLM) under two conditions: with and without the retrieved documents. Instead of relying solely on each token's immediate sensitivity to the retrieved documents, CORTEX also leverages the propagation of document-grounded information through preceding tokens, reducing false positives for tokens whose evidence has already been absorbed into the context. Finally, CORTEX applies post-processing smoothing step that models the tendency of hallucination labels to persist over contiguous spans, reducing local noise and encouraging span-consistent predictions. Experiments on two RAG benchmarks and three LLMs show that CORTEX substantially improves token-level hallucination detection, with each component consistently contributing to performance gains.

Developmental approach reveals the statistical learning of Neural Language Models: Transformers generalize from the most abstract statistical patterns

In this study, we use a developmental approach to investigate the statistical learning and mental representation of neural language models (NLM). A series of Generative Transformer models are trained on a synthetic grammar. The model states are saved at multiple stages in the course of training. Through analyzing how the internal representations of these models change in the developmental path, we found that NLMs acquire the most abstract global statistical knowledge at the beginning of learning and later acquire the relatively local statistical dependencies. This learning path contains many over-generalizations from the very beginning and these over-generalizations are gradually constrained in the later stage of learning. Based on this observation, we propose a new framework to explain the statistical learning and language cognition of NLMs.