← Back to all news
arXiv AI By Danchun Chen, Qiyao Yan, Chenpeng Wang, Liangming Pan

Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models

Read the original on arXiv AI →

The paper investigates how large language models perform propositional logical reasoning by conducting a causal mechanistic analysis on the PropLogic-MI benchmark. It identifies four interlocking mechanisms—Staged Computation, Information Transmission, Fact Retrospection, and Specialized Attention Heads—that organize the reasoning process across layers. The study demonstrates that these mechanisms recur across different model families, rule categories, and reasoning hops, indicating a structured, layer‑organized internal process for propositional reasoning.

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 AI.

Related stories

arXiv Machine Learning
Jun 9

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

arXiv:2510. 13554v2 Announce Type: replace-cross Abstract: The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps.

By Yang Li, Zhichen Dong, Yuhan Sun, Weixun Wang, Shaopan Xiong, Yijia Luo, Jiashun Liu, Han Lu, Jiamang Wang, Wenbo Su, Bo Zheng, Junchi Yan
llmsreinforcement-learning
More like this →
arXiv Computation and Language
Nov 4

Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning

The paper investigates a phenomenon called Echo of Prompt (EOP), where large language models spontaneously restate the question at the beginning of their chain-of-thought reasoning. By formalizing EOP’s probabilistic cost and measuring its impact on accuracy, the authors show that reinserting echoes can improve exact match scores on reasoning benchmarks and that EOP shifts attention toward answer tokens in middle layers. They further propose Echo-Distilled SFT and Echoic Prompting techniques that leverage echoing to enhance performance across several math reasoning datasets.

By Zhuoyuan Hao, Zhuo Li, Wu Li, Fangming Liu, Min Zhang, Jing Li
llmsfine-tuning
More like this →