ACL Findings2025
Verbosity-Aware Rationale Reduction: Sentence-Level Rationale Reduction for Efficient and Effective Reasoning
Joonwon Jang, Jaehee Kim, Wonbin Kweon, Seonghyeon Lee, Hwanjo Yu
Abstract
Large Language Models (LLMs) rely on generating extensive intermediate reasoning units (e.g., tokens, sentences) to enhance final answer quality across a wide range of complex tasks. While this approach has proven effective, it inevitably increases substantial inference costs. Previous methods adopting token-level reduction without clear criteria result in poor performance compared to models trained with complete rationale. To address this challenge, we propose a novel sentence-level rationale reduction framework leveraging likelihood-based criteria, verbosity, to identify and remove redundant reasoning sentences. Unlike previous approaches, our method leverages verbosity to selectively remove redundant reasoning sentences while preserving reasoning capabilities. Our experimental results across various reasoning tasks demonstrate that our method improves performance by an average of 7.71% while reducing token generation by 19.87% compared to model trained with complete reasoning paths.
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.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
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 Self-Refine: Iterative Refinement with Self-Feedback
- Reflexion: language agents with verbal reinforcement learning cites Self-Refine: Iterative Refinement with Self-Feedback
- Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models cites Reflexion: language agents with verbal reinforcement learning
Cited by top-tier papers1
Builds on12
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 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
- Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 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
Related papers
- Rethinking LLM Reasoning: From Explicit Trajectories to Latent RepresentationsCong Jiang, Xiaofeng Zhang, Fangzhi Zhu, XiaoWei Chen et al.ICLR 2026
- Think Clearly: Improving Reasoning via Redundant Token PruningDaewon Choi, Jimin Lee, Jihoon Tack, Woomin Song et al.EMNLP Findings 2025
- LIMOPro: Reasoning Refinement for Efficient and Effective Test-time ScalingYang Xiao, Jiashuo Wang, Ruifeng Yuan, Chunpu Xu et al.NeurIPS 2025 · 15 citations
- Do LLMs Encode Functional Importance of Reasoning Tokens ?Janvijay Singh, Dilek Hakkani-TürACL 2026 · 3 citations
- Logic-Thinker: Teaching Large Language Models to Think more LogicallyChengyao Wen, Qiang Cheng, Shaofei Wang, Zhizhen Liu et al.EMNLP Findings 2025
