ACL Findings2026
Where Reasoning Breaks: Logic-Aware Path Selection by Controlling Logical Connectives in LLMs Reasoning Chains
Seunghyun Park, Yuanyuan Lei
Abstract
While LLMs demonstrate impressive reasoning capabilities, they remain fragile in multi-step logic deduction, where a single transition error can propagate through the entire reasoning chain, leading to unstable performance. In this work, we identify logical connectives as primary points of this structural fragility. Through empirical analysis, we show that logical connective tokens function as high entropy forking points, at which models frequently struggle to determine the correct logical direction. Motivated by this observation, we hypothesize that intervening in logical connective selection can guide LLMs towards the correct logical direction, thereby improving the overall reasoning chain. To validate this hypothesis, we propose a multi-layered framework that intervenes specifically at these logic-critical junctions in the reasoning process. Specifically, we introduce (1) Gradient-based Logical Steering to guide LLMs internal representations towards valid reasoning subspaces, (2) Localized Branching to resolve ambiguity via targeted look-ahead search, and (3) Targeted Transition Preference Optimization, a surgical reinforcement learning objective that selectively optimizes singletoken preferences at logical pivots. Crucially, by concentrating intervention solely on logiccritical transitions, our framework achieves a favorable accuracy-efficiency trade-off compared to global inference time scaling methods like beam search and self-consistency 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Let's Verify Step by Step cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Let's Verify Step by Step cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds on18
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
- Let's Verify Step by StepHunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards et al.ICLR 2024 · 3,045 citations
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
- Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM ReasoningShenzhi Wang, Le Yu, Chang Gao, Chujie Zheng et al.NeurIPS 2025 · 592 citations
Related papers
- Dissecting Failure Dynamics in Large Language Model ReasoningWei Zhu, Jian Zhang, Lixing Yu, Kun Yue et al.ACL 2026 · 2 citations
- RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement LearningQianyue Hao, Sibo Li, Jian Yuan, Yong LiICLR 2026 · 20 citations
- LSEG: A Fine-tuning Free Method for NL2FOL via Logic-Structure and Entropy Guided Inference ControllingYuwei Huang, Shi Wang, Kangli Zi, Tianyu Luo et al.ACL Findings 2026
- Attention Illuminates LLM Reasoning: The Uncovered Preplan-and-Anchor Rhythm Enables Fine-Grained Policy OptimizationYang Li, Zhichen Dong, Yuhan Sun, Weixun Wang et al.ICML 2026 · 25 citations
- Reasoning with Exploration: An Entropy PerspectiveDaixuan Cheng, Shaohan Huang, Xuekai Zhu, Bo Dai et al.AAAI 2026 · 216 citations
