中文
相关论文

相关论文: Question Decomposition Improves the Faithfulness o…

200 篇论文

Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (CoT) practices. However, whether fundamental reasoning…

计算与语言 · 计算机科学 2026-05-28 Xingwei Tan , Marco Valentino , Mahmud Elahi Akhter , Yuxiang Zhou , Maria Liakata , Nikolaos Aletras

Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thought. Through…

人工智能 · 计算机科学 2024-09-04 Evelyn Yee , Alice Li , Chenyu Tang , Yeon Ho Jung , Ramamohan Paturi , Leon Bergen

Large Language Models (LLMs) frequently produce factually inaccurate outputs - a phenomenon known as hallucination - which limits their accuracy in knowledge-intensive NLP tasks. Retrieval-augmented generation and agentic frameworks such as…

Chain-of-thought (CoT) prompting is a common technique for improving the reasoning abilities of large language models (LLMs). However, extended reasoning is often unnecessary and substantially increases token usage. As such, a key question…

计算与语言 · 计算机科学 2026-01-09 Samuel Lewis-Lim , Xingwei Tan , Zhixue Zhao , Nikolaos Aletras

Chain of Thought (CoT) prompting can encourage language models to engage in multi-step logical reasoning. The quality of the provided demonstrations significantly influences the success of downstream inference tasks. Current unsupervised…

计算与语言 · 计算机科学 2025-05-27 Yufeng Zhang , Xuepeng Wang , Lingxiang Wu , Jinqiao Wang

While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. faithfulness). We…

计算与语言 · 计算机科学 2023-09-22 Qing Lyu , Shreya Havaldar , Adam Stein , Li Zhang , Delip Rao , Eric Wong , Marianna Apidianaki , Chris Callison-Burch

Studies have underscored how, regardless of the recent breakthrough and swift advances in AI research, even state-of-the-art Large Language models (LLMs) continue to struggle when performing logical and mathematical reasoning. The results…

人工智能 · 计算机科学 2024-12-20 Federico Castagna , Isabel Sassoon , Simon Parsons

Recent years have witnessed significant progress in large language models' (LLMs) reasoning, which is largely due to the chain-of-thought (CoT) approaches, allowing models to generate intermediate reasoning steps before reaching the final…

计算与语言 · 计算机科学 2025-04-15 Zuoli Tang , Junjie Ou , Kaiqin Hu , Chunwei Wu , Zhaoxin Huan , Chilin Fu , Xiaolu Zhang , Jun Zhou , Chenliang Li

Large language models (LLMs) demonstrate their promise in tackling complicated practical challenges by combining action-based policies with chain of thought (CoT) reasoning. Having high-quality prompts on hand, however, is vital to the…

机器学习 · 计算机科学 2024-03-01 Xue Yan , Yan Song , Xinyu Cui , Filippos Christianos , Haifeng Zhang , David Henry Mguni , Jun Wang

Chain-of-thought (CoT) reasoning generated by large language models (LLMs) is often unfaithful: intermediate steps can be logically inconsistent or fail to reflect the causal relationship leading to the final answer. Despite extensive…

机器学习 · 计算机科学 2026-02-03 Fuxin Wang , Amr Alazali , Yiqiao Zhong

Large Language Models (LMs) have achieved state-of-the-art performance on many Natural Language Processing (NLP) benchmarks. With the growing number of new benchmarks, we build bigger and more complex LMs. However, building new LMs may not…

计算与语言 · 计算机科学 2022-10-28 Pruthvi Patel , Swaroop Mishra , Mihir Parmar , Chitta Baral

Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought (CoT) prompting. However, CoT prompting greatly increases computational demands, which has prompted growing interest in distilling CoT capabilities into Small…

计算与语言 · 计算机科学 2025-05-28 Xinghao Chen , Zhijing Sun , Wenjin Guo , Miaoran Zhang , Yanjun Chen , Yirong Sun , Hui Su , Yijie Pan , Dietrich Klakow , Wenjie Li , Xiaoyu Shen

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

Chain-of-thought (CoT), tree-of-thought (ToT), and related techniques work surprisingly well in practice for some complex reasoning tasks with Large Language Models (LLMs), but why? This work seeks the underlying reasons by conducting…

人工智能 · 计算机科学 2024-06-19 Liwei Kang , Zirui Zhao , David Hsu , Wee Sun Lee

Chain of Thought (CoT) reasoning has demonstrated remarkable deep reasoning capabilities in both large language models (LLMs) and multimodal large language models (MLLMs). However, its reliability is often undermined by the accumulation of…

人工智能 · 计算机科学 2025-11-26 Zijun Chen , Wenbo Hu , Richang Hong

Despite demonstrating emergent reasoning abilities, Large Language Models (LLMS) often lose track of complex, multi-step reasoning. Existing studies show that providing guidance via decomposing the original question into multiple…

计算与语言 · 计算机科学 2024-04-04 Gurusha Juneja , Subhabrata Dutta , Tanmoy Chakraborty

Chain of Thought (CoT) is significant in improving the reasoning abilities of large language models (LLMs). However, the correlation between the effectiveness of CoT and the length of reasoning steps in prompts remains largely unknown. To…

计算与语言 · 计算机科学 2024-06-25 Mingyu Jin , Qinkai Yu , Dong Shu , Haiyan Zhao , Wenyue Hua , Yanda Meng , Yongfeng Zhang , Mengnan Du

Table-based reasoning has shown remarkable progress in combining deep models with discrete reasoning, which requires reasoning over both free-form natural language (NL) questions and structured tabular data. However, previous table-based…

计算与语言 · 计算机科学 2023-04-28 Yunhu Ye , Binyuan Hui , Min Yang , Binhua Li , Fei Huang , Yongbin Li

Cognitive Reframing, a core element of Cognitive Behavioral Therapy (CBT), helps individuals reinterpret negative experiences by finding positive meaning. Recent advances in Large Language Models (LLMs) have demonstrated improved…

计算与语言 · 计算机科学 2025-04-02 Yilin Qi , Dong Won Lee , Cynthia Breazeal , Hae Won Park

Scaling inference compute enhances reasoning in large language models (LLMs), with long chains-of-thought (CoTs) enabling strategies like backtracking and error correction. Reinforcement learning (RL) has emerged as a crucial method for…

计算与语言 · 计算机科学 2025-02-06 Edward Yeo , Yuxuan Tong , Morry Niu , Graham Neubig , Xiang Yue