Home Knowledge Base Hidden States

Hidden States

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory

Announce Type: new Abstract: Recurrent neural networks maintain a hidden state $h_t$, but its probabilistic meaning is often unclear. We study hidden-state stability through \emph{backward coherence}: the extent to which $h_t$ can be reconstructed from $h_{t+1}$ by a learned backward projector $g_\phi$. Under contraction and summable backward drift, the hidden-state sequence forms a quasi-reverse-martingale. This yields almost-sure convergence, rates under mixing, an interpretable limiting...

arXiv CS 1d ago

Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs

arXiv:2606.02628v1 Announce Type: new Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal is strongest. Across three $7$B--$8$B instruction-tuned models (Llama-3.1-8B, Mistral-7B, Qwen2.5-7B) loaded in $4$-bit NF4 quantization, we extract per-layer hidden states on four hallucination benchmarks (TruthfulQA, HaluEval-QA, FEVER, and a controlled synthetic set) and compare four detection...

arXiv CS 7d ago

Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States

Announce Type: replace Abstract: Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning types. We test this by probing Qwen3-14B on three benchmarks spanning the classical trichotomy: LogiQA 2.0 (deductive), ARC-Challenge (inductive), and $\alpha$NLI (abductive). At layer 32 of 40, linear probes achieve 100\% cross-validated accuracy with well-separated geometry (intrinsic dimensionalities: 20.6,...

arXiv CS 5d ago

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning

Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has become the dominant approach for improving mathematical reasoning in large language models, yet current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states. Investigating this structure, we find that at the anchor token (the position immediately before the answer marker), correct rollouts converge naturally because they must produce...

arXiv CS 7d ago

Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States

arXiv:2606.02907v1 Announce Type: new Abstract: Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning types. We test this by probing Qwen3-14B on three benchmarks spanning the classical trichotomy: LogiQA 2.0 (deductive), ARC-Challenge (inductive), and $\alpha$NLI (abductive). At layer 32 of 40, linear probes achieve 100\% cross-validated accuracy with well-separated geometry (intrinsic...

arXiv CS 7d ago

Author Correction: Hidden states and dynamics of fractional fillings in twisted MoTe<sub>2</sub> bilayers

Nature, Published online: 29 May 2026; doi:10.1038/s41586-026-10717-yAuthor Correction: Hidden states and dynamics of fractional fillings in twisted MoTe2 bilayers

Nature 12d ago

What Am I Missing? Question-Answering as Hidden State Probing

arXiv:2605.31561v1 Announce Type: new Abstract: Test-time reasoning has become a significant field of study since the introduction of chain-of-thought reasoning in large language models (LLMs). However, the mechanisms of this reasoning process are still under-explored -- from the same input prompt, and even the same partial solution, LLMs can produce varied answers if sampled multiple times. We propose to leverage question-asking as an inference-time intervention that articulates information...

arXiv CS 9d ago

Beyond Generative Decoding: Discriminative Hidden-State Readout from a Native Omni-Modal LLM for Multimodal Sentiment Analysis

arXiv:2606.05713v1 Announce Type: new Abstract: Multimodal sentiment analysis (MSA) infers human affect from language, acoustic, and visual signals. Recent methods increasingly adapt large multimodal models (LMMs) via generative readout: prompting the model to emit a sentiment score as a text string. While convenient, this ties continuous regression to discrete autoregressive decoding, incurring unmeasured costs.

arXiv CS 5d ago

Trajectory Dynamics in Language Model Hidden States Predict Human Processing Costs Beyond Surprisal

arXiv:2606.05346v1 Announce Type: new Abstract: Human language comprehension unfolds sequentially: each word is processed in the context of those that came before, and the interpretation builds incrementally over time. Surprisal, the negative log probability of a word given its context, has been the dominant predictor of incremental processing cost. But surprisal reduces rich sequential representations to a single scalar at each word, discarding information about the direction in which the...

arXiv CS 5d ago

A Direct Approach for Handling Contextual Bandits with Latent State Dynamics

Announce Type: replace Abstract: We consider a linear contextual bandit model where contexts and rewards are governed by a finite hidden Markov chain. We first revisit the simplified model by Nelson et al. (2022), in which rewards are linear functions of the posterior probabilities over the hidden states given the observed contexts (called beliefs), rather than functions of the hidden states themselves.

arXiv CS 8d ago