arXiv Machine Learning September 23, 2026 By Marios Papamichalis, Regina Ruane

What Does Chain-of-Thought Entropy Measure? A Channel Audit of Scaffolding, Routing, and Content

Read the original on arXiv Machine Learning →

The paper investigates how entropy over chain‑of‑thought tokens influences policy decisions such as gradient application, pruning, and collapse detection. By separating scaffold tokens from substantive content, the authors analyze entropy, Kullback–Leibler divergence, and entropy velocity for each channel, proving differences between raw and content conventions and bounding answer diversity. Empirical results across 23 configurations show that scaffold tokens can account for up to 41% of high‑entropy positions, with entropy share growing through distillation, while content conventions outperform raw surprisal on compression tasks and reveal significant answer leakage in re‑fed chains.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 13

LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence

arXiv:2608. 11922v1 Announce Type: cross Abstract: Predictive-distribution entropy makes a strong selection rule in retrieval-augmented question answering: across five QA benchmarks, keeping the candidate answer that a frozen respondent LLM produces with the lowest answer-token entropy lifts mean answer $F_1$ from 0.

By Po-Jen Ko, Che-Cheng Wu, Hung-Chun Hsu, Li-Yang Chang, Chuan-Ju Wang

llms rag nlp reinforcement-learning benchmarks

arXiv AI

Jun 19

Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning

arXiv:2606. 19771v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced Large Language Model (LLM) reasoning; however, it faces a fundamental optimization instability: uniform token updates precipitate entropy collapse, leading to premature convergence to suboptimal strategies, whereas excessive Shannon Entropy maximization can cause entropy explosion, driving blind exploration toward incoherent reasoning chains.

By Xuanzhi Feng, Zhengyang Li, Zeyu Liu, Haoxi Li, Yuming Jiang, Bing Guo, Jingcai Guo, Jie Zhang, Song Guo

llms reinforcement-learning benchmarks

arXiv AI

Sep 15

LLM Probability Concentration: How Alignment Shrinks the Generative Horizon

arXiv:2506.17871v4 Announce Type: replace-cross Abstract: Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this cons...

By Chenghao Yang, Sida Li, Ari Holtzman

llms safety

arXiv AI

Aug 12

Attention-Path Fragility as an Uncertainty Signal in Large Language Models

arXiv:2608. 11138v1 Announce Type: cross Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident prediction is \emph{fragile} under perturbation of its attention pathways.

By Minsoo Kim, Sungyoung Ji, Kisung Moon, Ilyong Yoon

llms benchmarks

arXiv Machine Learning

Aug 18

Cross-Entropy Risk Estimation for Language Models: Inconsistency Must Be Dense, and the Holdout Method Is No Exception

arXiv:2608. 15798v1 Announce Type: new Abstract: Language models are compared by their held-out per-token cross-entropy risk---the quantity scaling laws are fitted to.

By Hanti Lin

llms

arXiv AI

Jun 30

Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters

arXiv:2606. 30128v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting improves LLM reasoning, but the source is contested: do the intermediate steps help because they carry useful semantic content, or because conditioning on more tokens buys extra computation before the model commits to an answer?

By Wenlong Wang, Fergal Reid

llms benchmarks

One email a morning, machine-written

Related stories

LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence

Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning

LLM Probability Concentration: How Alignment Shrinks the Generative Horizon

Attention-Path Fragility as an Uncertainty Signal in Large Language Models

Cross-Entropy Risk Estimation for Language Models: Inconsistency Must Be Dense, and the Holdout Method Is No Exception

Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters