English
Related papers

Related papers: From Explicit CoT to Implicit CoT: Learning to Int…

200 papers

Chain-of-Thought (CoT) and Program-Aided Language Models (PAL) represent two distinct reasoning methods, each with its own strengths. CoT employs natural language, offering flexibility and interpretability, while PAL utilizes programming…

Computation and Language · Computer Science 2023-10-24 James Xu Zhao , Yuxi Xie , Kenji Kawaguchi , Junxian He , Michael Qizhe Xie

Large language models (LLMs) exhibit strong reasoning abilities, often attributed to few-shot or zero-shot chain-of-thought (CoT) prompting. While effective, these methods require labor-intensive prompt engineering, raising the question of…

Computation and Language · Computer Science 2025-03-19 Hyunbin Jin , Je Won Yeom , Seunghyun Bae , Taesup Kim

Chain-of-thought (CoT) prompting is necessary for arithmetic in small language models, yet shuffling its steps preserves most performance. What does CoT contribute if not logical sequencing? In three 1-3B instruction-tuned LMs on GSM8K, we…

Machine Learning · Computer Science 2026-05-25 Ming Liu

Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks by generating intermediate reasoning steps. However, most existing approaches focus on hard token decoding, which constrains reasoning…

Computation and Language · Computer Science 2025-05-28 Yige Xu , Xu Guo , Zhiwei Zeng , Chunyan Miao

Large Language Models (LLMs) have demonstrated significant improvements in reasoning capabilities through supervised fine-tuning and reinforcement learning. However, when training reasoning models, these approaches are primarily applicable…

Computation and Language · Computer Science 2025-05-16 Yoichi Ishibashi , Taro Yano , Masafumi Oyamada

Chain-of-Thought (CoT) reasoning enhances the problem-solving ability of large language models (LLMs) but leads to substantial inference overhead, limiting deployment in resource-constrained settings. This paper investigates efficient CoT…

Artificial Intelligence · Computer Science 2025-12-03 Ziqian Bi , Kaijie Chen , Tianyang Wang , Junfeng Hao , Benji Peng , Xinyuan Song

Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computational overhead for inference. Existing CoT compression methods often suffer from a critical…

Machine Learning · Computer Science 2026-05-26 Yuntian Tang , Bohan Jia , Wenxuan Huang , Lianyue Zhang , Jiao Xie , Wenxi Li , Wei Li , Jie Hu , Xinghao Chen Rongrong Ji , Shaohui Lin

Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They struggle, however, when the necessary knowledge…

Computation and Language · Computer Science 2023-06-26 Harsh Trivedi , Niranjan Balasubramanian , Tushar Khot , Ashish Sabharwal

Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctness is no longer tied to a single reasoning trace but to the aggregation rule over a pool…

Machine Learning · Statistics 2026-05-15 Yu Gu , Zijun Yu , Vahid Partovi Nia , Masoud Asgharian

Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a ``chain-of-thought'' (CoT) prompt. One can also improve LLMs' performance on a specific task by…

Robot chain-of-thought reasoning (CoT) -- wherein a model predicts helpful intermediate representations before choosing actions -- provides an effective method for improving the generalization and performance of robot policies, especially…

Robotics · Computer Science 2025-05-20 William Chen , Suneel Belkhale , Suvir Mirchandani , Oier Mees , Danny Driess , Karl Pertsch , Sergey Levine

We study how to extend chain-of-thought (CoT) beyond language to better handle multimodal reasoning. While CoT helps LLMs and VLMs articulate intermediate steps, its text-only form often fails on vision-intensive problems where key…

Artificial Intelligence · Computer Science 2026-02-03 Yifei Shao , Kun Zhou , Ziming Xu , Mohammad Atif Quamar , Shibo Hao , Zhen Wang , Zhiting Hu , Biwei Huang

Chain-of-Thought (CoT) prompting helps models think step by step. But naive CoT breaks down in visually grounded social tasks, where models must perceive, understand, and judge all at once; bridging perception with norm-grounded reasoning.…

Computation and Language · Computer Science 2026-04-21 Eunkyu Park , Wesley Hanwen Deng , Gunhee Kim , Motahhare Eslami , Maarten Sap

Large vision language models exhibit notable limitations on Geometry Problem Solving (GPS) because of their unreliable diagram interpretation and pure natural-language reasoning. A recent line of work mitigates this by using symbolic…

Machine Learning · Computer Science 2025-08-13 Tianyun Yang , Yunwen Li , Ziniu Li , Zhihang Lin , Ruoyu Sun , Tian Ding

We demonstrate that a developmentally ordered curriculum markedly improves reasoning transparency and sample-efficiency in small language models (SLMs). Concretely, we train Cognivolve, a 124 M-parameter GPT-2 model, on a four-stage…

Computation and Language · Computer Science 2025-05-20 Xiang Fu

Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…

Machine Learning · Computer Science 2023-11-02 Fabien Roger , Ryan Greenblatt

Long chain-of-thought (CoT) is an essential ingredient in effective usage of modern large language models, but our understanding of the reasoning strategies underlying these capabilities remains limited. While some prior works have…

Computation and Language · Computer Science 2025-05-16 Seongyun Lee , Seungone Kim , Minju Seo , Yongrae Jo , Dongyoung Go , Hyeonbin Hwang , Jinho Park , Xiang Yue , Sean Welleck , Graham Neubig , Moontae Lee , Minjoon Seo

Recent advancements in large language models (LLMs) have demonstrated their impressive abilities in various reasoning and decision-making tasks. However, the quality and coherence of the reasoning process can still benefit from enhanced…

Computation and Language · Computer Science 2025-01-24 Shihao Ji , Zihui Song , Fucheng Zhong , Jisen Jia , Zhaobo Wu , Zheyi Cao , Tianhao Xu

Chain-of-Though (CoT) represents a common strategy for reasoning in Large Language Models (LLMs) by decomposing complex tasks into intermediate inference steps. However, explanations generated via CoT are susceptible to content biases that…

Computation and Language · Computer Science 2026-03-31 Leonardo Ranaldi , Marco Valentino , Andrè Freitas

Using Large Language Models for complex mathematical reasoning is difficult, primarily due to the complexity of multi-step reasoning. The main challenges of this process include (1) selecting critical intermediate results to advance the…

Artificial Intelligence · Computer Science 2024-02-29 Zilong Zhao , Yao Rong , Dongyang Guo , Emek Gözlüklü , Emir Gülboy , Enkelejda Kasneci