6arXiv cs.CL (Computation and Language)·
Linear probes reveal LLMs encode remaining output length in hidden states
Researchers trained minimal linear probes on frozen hidden states of three open-weight 7-8B models and found that total response length is linearly decodable from the prompt's final hidden state before any output is generated. The probe directions transfer across natural-language and synthetic datasets, and per-position estimates shift upward when models retract and restart partial solutions. The authors interpret this as evidence that LLMs maintain a plan-like internal representation of remaining generation length, distinct from exact-counting, though causality is not established.
Related guides (1)
Related events (8)
Probe Trajectories Reveal Reasoning Dynamics in Large Reasoning Models
This paper investigates whether hidden representations of Large Reasoning Models (LRMs) can predict future model behavior by analyzing probe trajectories—the continuous evolution of concept probabilities across Chain-of-Thought reasoning tokens. The authors find that temporal trajectory features (volatility, trend, steady-state) significantly outperform single static probes, with max-pooling achieving up to 95% AUROC across safety and mathematics domains. Two methodological insights are offered: template-based training data matches dynamically generated responses in quality, and pooling strategy is critical to probe performance. The work positions probe trajectories as a complementary safety monitoring framework for LRMs where CoT faithfulness cannot be assumed.
Question-Answering as Hidden State Probing for Test-Time Reasoning Intervention
This paper proposes using question-asking as an inference-time intervention to surface information about an LLM's hidden state during chain-of-thought reasoning. The authors train a probe on a student model's hidden states before and after question generation, finding it predictive of final answer correctness even before the teacher responds—suggesting self-diagnosis during question generation carries meaningful signal. They frame question-asking as a sequential decision problem with a gating policy, but find a gap between detection and recovery: interventions are as likely to harm correct trajectories as to fix incorrect ones. The results have implications for the limits of LLM self-refinement under uncertainty.
Disentangling solvability knowledge from verbalization in LLM hidden states
A new arXiv preprint probes LLM internal representations to separately decode 'solvability knowledge' and 'verbalization' as distinct linear directions in hidden states. The authors find that fabrication (hallucination of solutions to unsolvable problems) is primarily driven by shifts in verbalization representations rather than underlying knowledge. Prompting with unsolvability cues and activation steering can mechanistically shift verbalization to improve model abstention. The work advances mechanistic understanding of why LLMs confabulate on unsolvable math problems.
Mechanistic analysis of how LLMs encode essay quality in internal representations
Researchers systematically probe the hidden representations of eight LLMs across three essay datasets (ASAP++, CSEE, ENEM) to understand how automated essay scoring (AES) works internally. Using linear probing, dimensionality reduction, and neuron-level analysis, they find essay quality is encoded in a linearly accessible form that emerges progressively across layers and partially transfers across prompts. Individual 'essay scoring neurons' are identified whose activations correlate with scores and respond to targeted interventions, with longer essays relying more on deeper layers. The work contributes to mechanistic interpretability of LLM-based scoring systems.
Language models linearly encode a 'value axis' tracking expected goal success, study finds
Researchers construct a 'value axis' in Qwen3-8B's activation space using synthetic in-context RL data, finding that this axis distinguishes high vs. low confidence, backtracking vs. non-backtracking rollouts, and correct vs. corrupted code. Steering along this axis causally modulates self-correction behavior and verbosity, while DPO training shifts the internal value of rewarded behaviors. Applied to real-world settings, the axis reveals that Qwen assigns low internal value to politically sensitive queries post-training and that SFT increases domain-specific confidence. The findings suggest LLMs linearly encode an estimate of expected goal success that shapes their generative behavior.
LLMs fail to reliably self-report adversarial prefill attacks, study finds
A new arXiv paper evaluates whether LLMs can recognize that their own prior responses were elicited by adversarial prefill attacks, testing ten open-weight models (3B–70B) across four safety benchmarks. Models claim intent on prefilled responses only 27.3% of the time on average, and introspective signal is largely mediated by refusal-related reasoning. Three LoRA fine-tuning methods (SFT, GRPO, DPO) improve the intention-probe gap but counterintuitively raise attack success rates on most models, suggesting partial and fragile mitigation. The findings raise concerns about the reliability of LLM self-reports in safety-critical contexts.
PAC-Bayes analysis establishes formal expressivity and alignment floors for prompt-conditioned LLMs
A new arXiv preprint models user-LLM interaction as a bilevel cheap-talk game and derives PAC-Bayes bounds showing two irreducible limitations: an 'expressivity floor' where language's finite channel capacity makes distinct tasks indistinguishable, and an 'objective-misalignment floor' where alignment constraints prevent reaching user-ideal outputs. The authors prove that prompt-conditioned LLMs cannot be universal problem solvers, as correct behavior on certain task families is provably unattainable even with infinite data, optimal training, or model scaling. The work suggests multimodal inputs and external memory as potential mitigations by increasing task-relevant information bandwidth.
A Sleep-Like Consolidation Mechanism for LLMs
A preprint on arXiv proposes a sleep-like memory consolidation mechanism for large language models, drawing an analogy to biological sleep-based memory consolidation in neural systems. The work appears to address how LLMs might better retain and integrate new information over time, a key challenge in continual learning and knowledge updating. The paper attracted notable community attention on Hacker News with 164 points and 122 comments, suggesting broad interest in the approach.