EDIS: Diagnosing LLM Reasoning via Entropy Dynamics

• URL: http://arxiv.org/abs/2602.01288v1
• Date: Sun, 01 Feb 2026 15:43:50 GMT
• Title: EDIS: Diagnosing LLM Reasoning via Entropy Dynamics
• Authors: Chenghua Zhu, Siyan Wu, Xiangkang Zeng, Zishan Xu, Zhaolu Kang, Yifu Guo, Yuquan Lu, Junduan Huang, Guojing Zhou,
• Abstract summary: We show that the emphtemporal evolution of confidence during generation carries richer information than aggregate statistics alone.<n>We introduce the Entropy Dynamics Instability Score (textbfEDIS), a trajectory-level metric quantifying instability in entropy evolution.
• Score: 3.858418431840288
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Entropy-based confidence signals are increasingly leveraged to improve reasoning in large language models (LLMs), yet existing approaches treat confidence as a static quantity -- typically aggregated over tokens. We show that the \emph{temporal evolution} of confidence during generation carries richer information than aggregate statistics alone. Analyzing token-level entropy trajectories, we identify characteristic patterns distinguishing correct from incorrect reasoning: erroneous solutions exhibit unstable dynamics, including burst spikes (sustained uncertainty growth) and peak-valley spikes (sharp rebounds following transient confidence). These patterns persist across models and training stages, suggesting they reflect intrinsic properties of reasoning failure rather than superficial noise. To formalize this observation, we introduce the Entropy Dynamics Instability Score (\textbf{EDIS}), a trajectory-level metric quantifying instability in entropy evolution. EDIS serves as an effective diagnostic signal for inference-time selection, substantially improving reasoning accuracy, and offers a promising direction for training-time sample curation. Our findings establish entropy dynamics as an underexplored yet informative lens for understanding and improving LLM reasoning.

Related papers

• Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives [22.29000001610794]
  Standard negative log-likelihood for Supervised Fine-Tuning (SFT) applies uniform token-level weighting.<n>This rigidity creates a two-fold failure mode: (i) overemphasizing low-probability targets can amplify gradients on noisy supervision and disrupt robust priors, and (ii) uniform weighting provides weak sharpening when the model is already confident.<n>Existing methods fail to resolve the resulting plasticity--stability dilemma, often suppressing necessary learning signals alongside harmful ones.<n>We introduce Dynamic Entropy Fine-Tuning (DEFT), a parameter-free objective that modulates the
  arXiv  Detail & Related papers  (2026-02-11T22:56:43Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns [51.02752099869218]
  Large Language Models (LLMs) display strikingly different generalization behaviors.<n>We introduce a novel benchmark that decomposes reasoning into atomic core skills.<n>We show that RL-tuned models maintain more stable behavioral profiles and resist collapse in reasoning skills, whereas SFT models exhibit sharper drift and overfit to surface patterns.
  arXiv  Detail & Related papers  (2025-12-30T08:16:20Z)
• Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs [0.4115305983711515]
  This project develops a self correcting framework for large language models (LLMs)<n>Rather than relying solely on final answer correctness, our approach leverages fine grained uncertainty signals.<n>We design a composite reward function that penalizes unjustified high confidence and entropy spikes.
  arXiv  Detail & Related papers  (2025-11-19T23:09:26Z)
• Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG [35.96258615258145]
  We introduce Entropy-Trend Constraint (ETC), a training-free method that determines optimal retrieval timing by modeling the dynamics of token-level uncertainty.<n>ETC consistently outperforms strong baselines while reducing retrieval frequency.<n>It is plug-and-play, model-agnostic, and readily integrable into existing decoding pipelines.
  arXiv  Detail & Related papers  (2025-11-13T05:28:02Z)
• Revisiting Entropy in Reinforcement Learning for Large Reasoning Models [54.96908589622163]
  We investigate the entropy dynamics of large language models trained withReinforcement learning with verifiable rewards (RLVR)<n>Our findings reveal that the number of off-policy updates, the diversity of training data, and the clipping thresholds in the optimization objective are critical factors influencing the entropy of LLMs trained with RLVR.
  arXiv  Detail & Related papers  (2025-11-08T12:50:41Z)
• Identifiable learning of dissipative dynamics [25.409059056398124]
  We introduce I-OnsagerNet, a neural framework that learns dissipative dynamics directly from trajectories.<n>I-OnsagerNet extends the Onsager principle to guarantee that the learned potential is obtained from the stationary density.<n>Our approach enables us to calculate the entropy production and to quantify irreversibility, offering a principled way to detect and quantify deviations from equilibrium.
  arXiv  Detail & Related papers  (2025-10-28T07:57:14Z)
• Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective [11.65148836911294]
  entropy collapse is a rapid loss of policy diversity, stemming from the exploration-exploitation imbalance and leading to a lack of generalization.<n>Recent entropy-intervention methods aim to prevent coloredtextentropy collapse, yet their underlying mechanisms remain unclear.<n>We introduce an entropy-change-aware reweighting scheme, namely Stabilizing Token-level Entropy-changE via Reweighting (STEER)
  arXiv  Detail & Related papers  (2025-10-11T10:17:38Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM [6.7259418009996]
  Entropy Area Score (EAS) is a metric to quantify uncertainty in the answer generation process of large language models (LLMs)<n>EAS is both efficient and interpretable, offering a practical tool for uncertainty modeling and data quality assessment in LLM training.
  arXiv  Detail & Related papers  (2025-08-28T03:16:15Z)
• Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models [83.24079543652253]
  Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization.<n>However, reasoning-oriented RL fine-tuning significantly increases the prevalence of hallucinations.<n>We propose Factuality-aware Step-wise Policy Optimization (FSPO), an innovative RL fine-tuning algorithm incorporating explicit factuality verification.
  arXiv  Detail & Related papers  (2025-05-30T14:23:32Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.