Lune

EMNLP Findings2025

EoT: Evolution of Thoughts for Complex Reasoning Tasks

Qin Hua, Jiaqi Sun, Shiyou Qian, Dingyu Yang, Jian Cao, Guangtao Xue

Abstract

Knowledge-based complex reasoning remains a significant challenge for large language models (LLMs) with in-context learning. To tackle this issue, previous studies focus on ensuring behavior fidelity, factuality, or reliability in generated reasoning processes that guide LLMs to produce solutions. However, these studies often neglect the simultaneous optimization on all these three aspects for each thought. The main challenges are the lack of comprehensive assessment mechanisms and the difficulty of efficient thought-level optimization. This paper introduces the Evolution of Thoughts (EoT) framework, which enhances the factuality, fidelity, and reliability of each thought in the reasoning process through a few LLM inferences. We propose a thought assessment method that is sensitive to knowledge and LLM behaviors, using three scorers to evaluate each thought by considering domain context, semantic alignment, and behavior impact. Additionally, we establish a self-reflective evolution mechanism to facilitate each reasoning process generation in a single-forward inference. Extensive experiments demonstrate that, for knowledge-based complex tasks, EoT improves the factuality and fidelity of reasoning processes by approximately 16.5% and 48.8%, respectively, while enhancing LLM reasoning capability by about 6.2%, outperforming advanced approaches. 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.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Self-Consistency Improves Chain of Thought Reasoning in Language Models cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on10

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
  3. Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
  4. SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 citations
  5. 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

  1. Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM ReasoningZhenni Bi, Kai Han, Chuanjian Liu, Yehui Tang et al.ICML 2025
  2. Rectifying LLM Thought from Lens of OptimizationJunnan Liu, Hongwei Liu, Songyang Zhang, Kai ChenICLR 2026 · 3 citations
  3. Encoder of Thoughts: Enhancing Planning Ability in Language Agents Through Structural EmbeddingYuxiang Zhang, Jitao SangAAAI 2025 · 1 citation
  4. Everything of Thoughts: Defying the Law of Penrose Triangle for Thought GenerationRuomeng Ding, Chaoyun Zhang, Lu Wang, Yong Xu et al.ACL Findings 2024 · 15 citations
  5. Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model CommunicationZhangyue Yin, Qiushi Sun, Cheng Chang, Qipeng Guo et al.EMNLP 2023 · 15 citations
Dusk over the sea between two cliffs drawn in fine vertical lines