中文
相关论文

相关论文: To Reason or Not to: Selective Chain-of-Thought in…

200 篇论文

In the field of chemical engineering, traditional data-processing and prediction methods face significant challenges. Machine-learning and large-language models (LLMs) also have their respective limitations. This paper explores the…

机器学习 · 计算机科学 2025-02-19 Tianhang Zhou , Yingchun Niu , Xingying Lan , Chunming Xu

Large Language Models (LLMs) employ Chain-of-Thought (CoT) reasoning to deconstruct complex problems. While longer CoTs are often presumed superior, this paper challenges that notion, arguing that longer is not always better. Drawing on…

人工智能 · 计算机科学 2025-05-28 Yuyang Wu , Yifei Wang , Ziyu Ye , Tianqi Du , Stefanie Jegelka , Yisen Wang

Chain-of-thought (CoT) prompting has been widely adopted to enhance the reasoning capabilities of large language models (LLMs). However, the effectiveness of CoT reasoning is inconsistent across tasks with different reasoning types. This…

机器学习 · 计算机科学 2025-06-17 Yue Wan , Xiaowei Jia , Xiang Lorraine Li

Chain-of-thought (CoT) reasoning has been highly successful in solving complex tasks in natural language processing, and recent multimodal large language models (MLLMs) have extended this paradigm to video reasoning. However, these models…

计算机视觉与模式识别 · 计算机科学 2025-12-11 Yiwu Zhong , Zi-Yuan Hu , Yin Li , Liwei Wang

How much should a language agent think before taking action? Chain-of-thought (CoT) reasoning is widely assumed to improve agent performance, but the relationship between reasoning length and accuracy in structured tool-use settings remains…

计算与语言 · 计算机科学 2026-04-03 Xuan Qi

Recently, Chain-of-Thought (CoT) prompting has delivered success on complex reasoning tasks, which aims at designing a simple prompt like ``Let's think step by step'' or multiple in-context exemplars with well-designed rationales to elicit…

计算与语言 · 计算机科学 2024-06-04 Jianing Wang , Qiushi Sun , Xiang Li , Ming Gao

Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting. CoT prompting has two major paradigms. One…

计算与语言 · 计算机科学 2022-10-10 Zhuosheng Zhang , Aston Zhang , Mu Li , Alex Smola

While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate during inference. Non-verbal reasoning methods have emerged with shorter generation lengths by leveraging continuous…

计算与语言 · 计算机科学 2026-04-28 Keshav Ramji , Tahira Naseem , Ramón Fernandez Astudillo

Large Language Models (LLMs) have shown outstanding performance across wide range of downstream tasks. This competency is attributed to their substantial parameter size and pre-training on extensive corpus. Moreover, LLMs have exhibited…

计算与语言 · 计算机科学 2023-08-10 Yuhan Ma , Haiqi Jiang , Chenyou Fan

Chain of Thought (CoT) was introduced in recent research as a method for improving step-by-step reasoning in Large Language Models. However, CoT has limited applications such as its need for hand-crafted few-shot exemplar prompts and no…

计算与语言 · 计算机科学 2024-12-11 Arda Sevinc , Abdurrahman Gumus

Predicting cancer treatment outcomes requires models that are both accurate and interpretable, particularly in the presence of heterogeneous clinical data. While large language models (LLMs) have shown strong performance in biomedical NLP,…

计算与语言 · 计算机科学 2025-10-21 Raghu Vamshi Hemadri , Geetha Krishna Guruju , Kristi Topollai , Anna Ewa Choromanska

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 ICL approaches construct prompts using examples that contain…

计算与语言 · 计算机科学 2025-06-23 Zifan Xu , Haozhu Wang , Dmitriy Bespalov , Xian Wu , Peter Stone , Yanjun Qi

Reasoning large language models (LLMs) heavily rely on scaling test-time compute to perform complex reasoning tasks by generating extensive "thinking" chains. While demonstrating impressive results, this approach incurs significant…

计算与语言 · 计算机科学 2026-02-04 Michael Hassid , Gabriel Synnaeve , Yossi Adi , Roy Schwartz

Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-training methods. While longer reasoning traces can improve…

机器学习 · 计算机科学 2026-02-16 Qinhang Wu , Sen Lin , Ming Zhang , Yingbin Liang , Ness B. Shroff

Chain-of-Thought (CoT) prompting is a widely used inference-time technique for improving reasoning, yet its gains are uneven across tasks. We analyze when and why CoT helps by modeling the step-wise reasoning trajectory as a Markov chain.…

机器学习 · 计算机科学 2026-03-03 Zihan Wang , Yijun Dong , Qi Lei

Large language models (LLMs) excel in many tasks but struggle to accurately quantify uncertainty in their generated responses. This limitation makes it challenging to detect misinformation and ensure reliable decision-making. Existing…

计算与语言 · 计算机科学 2025-06-04 Boxuan Zhang , Ruqi Zhang

Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks. However, overthinking in long CoT not only slows down the efficiency of…

计算与语言 · 计算机科学 2025-09-30 Chenxu Yang , Qingyi Si , Yongjie Duan , Zheliang Zhu , Chenyu Zhu , Qiaowei Li , Minghui Chen , Zheng Lin , Weiping Wang

Large Reasoning Models (LRMs) achieve promising performance but compromise token efficiency due to verbose reasoning processes. Unconscious Thought Theory (UTT) posits that complex problems can be solved more efficiently through…

Chain-of-thought (CoT) reasoning boosts large language models' (LLMs) performance on complex tasks but faces two key limitations: a lack of reliability when solely relying on LLM-generated reasoning chains and lower reasoning performance…

计算与语言 · 计算机科学 2025-09-11 Feiyang Li , Peng Fang , Zhan Shi , Arijit Khan , Fang Wang , Weihao Wang , Xin Zhang , Yongjian Cui

This paper describes our submission to the MEDIQA-CORR 2024 shared task for automatically detecting and correcting medical errors in clinical notes. We report results for three methods of few-shot In-Context Learning (ICL) augmented with…

计算与语言 · 计算机科学 2024-06-14 Zhaolong Wu , Abul Hasan , Jinge Wu , Yunsoo Kim , Jason P. Y. Cheung , Teng Zhang , Honghan Wu