Lune

EMNLP Findings2024

LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning

Zifan Xu, Haozhu Wang, Dmitriy Bespalov, Xian Wu, Peter Stone, Yanjun Qi

去出版方阅读问 Lune

摘要

Chain-of-thought (CoT) prompting is a popular in-context learning (ICL) approach for large language models (LLMs), especially when tackling complex reasoning tasks. Traditional

问 Lune

尽管问，回答会引用原文。

Lune 会读完全文和相关的 Paper，每个回答都附上所依据的原文段落。

可以从这些问题问起

Lune 的依据

全文 · 引用它的 4 篇顶会 Paper · 相关的 Paper

获取答案

免费开始，无需绑卡

引用它的顶会 Paper4

  1. Hybrid Latent Reasoning via Reinforcement LearningZhenrui Yue, Bowen Jin, Huimin Zeng, Honglei Zhuang 等NeurIPS 2025 · 28 次引用
  2. The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will ThinkSeongyun Lee, Seungone Kim, Minju Seo, Yongrae Jo 等ICLR 2026 · 6 次引用
  3. Your Reasoning Model Knows What Counts: Self-Guided Chain-of-Thought Pruning for Efficient ReasoningZi-Ao Ma, Xian-Ling Mao, Tian Lan, Chen Xu 等ACL 2026
  4. CHOIR: Harmonizing Structured Persona Diversity for Robust Collaborative LLM ReasoningXiangjue Dong, Cong Wang, Maria Teleki, Millennium Bismay 等ACL 2026
问问它们各自怎么用它

它引用的 Paper19

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 64,255 次引用
  2. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 22,562 次引用
  3. Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo 等NeurIPS 2022 · 8,168 次引用
  4. Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu ChenICLR 2021 · 3,729 次引用
  5. Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order SensitivityYao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel 等ACL 2022 · 1,494 次引用

相关 Paper

  1. Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization AnalysisHongkang Li, Songtao Lu, Pin-Yu Chen, Xiaodong Cui 等ICLR 2025
  2. Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What MattersBoshi Wang, Sewon Min, Xiang Deng, Jiaming Shen 等ACL 2023 · 100 次引用
  3. Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMsXiang Zhang, Juntai Cao, Chenyu You, Dujian DingACL 2025 · 21 次引用
  4. Decomposed Prompting: A Modular Approach for Solving Complex TasksTushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu 等ICLR 2023 · 94 次引用
  5. Unveiling Factual Recall Behaviors of Large Language Models through Knowledge NeuronsYifei Wang, Yuheng Chen, Wanting Wen, Yu Sheng 等EMNLP 2024 · 3 次引用
黄昏的海面，两侧是细线勾勒的悬崖