中文
相关论文

相关论文: Internal Chain-of-Thought: Empirical Evidence for …

200 篇论文

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…

计算与语言 · 计算机科学 2025-04-16 Thilo Hagendorff , Sarah Fabi

Large language models (LLMs) have shown an impressive ability to perform tasks believed to require thought processes. When the model does not document an explicit thought process, it becomes difficult to understand the processes occurring…

计算与语言 · 计算机科学 2024-06-21 Yuval Shalev , Amir Feder , Ariel Goldstein

Large language models (LLMs) have demonstrated impressive capabilities, yet their internal mechanisms for handling reasoning-intensive tasks remain underexplored. To advance the understanding of model-internal processing mechanisms, we…

计算与语言 · 计算机科学 2026-04-20 Tanja Baeumel , Josef van Genabith , Simon Ostermann

Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decision-making. To support efficient reasoning, recent studies…

计算与语言 · 计算机科学 2025-09-03 Jindong Li , Yali Fu , Li Fan , Jiahong Liu , Yao Shu , Chengwei Qin , Menglin Yang , Irwin King , Rex Ying

Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…

计算与语言 · 计算机科学 2024-10-29 Zheng Zhao , Yftah Ziser , Shay B. Cohen

Large Language Models (LLMs) have demonstrated remarkable in-context learning (ICL) capabilities. In this study, we explore a surprising phenomenon related to ICL: LLMs can perform multiple, computationally distinct ICL tasks…

Large language models (LLMs) are typically prompted to follow a single instruction per inference call. In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as Multi-Task…

计算与语言 · 计算机科学 2024-06-07 Guijin Son , Sangwon Baek , Sangdae Nam , Ilgyun Jeong , Seungone Kim

Despite superior reasoning prowess demonstrated by Large Language Models (LLMs) with Chain-of-Thought (CoT) prompting, a lack of understanding prevails around the internal mechanisms of the models that facilitate CoT generation. This work…

计算与语言 · 计算机科学 2024-05-07 Subhabrata Dutta , Joykirat Singh , Soumen Chakrabarti , Tanmoy Chakraborty

Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent evidence presents a tension: hidden states appear to already encode future reasoning before CoT…

机器学习 · 计算机科学 2026-05-29 Liyan Xu , Mo Yu , Fandong Meng , Jie Zhou

Large language models (LLMs) with billions of parameters exhibit in-context learning abilities, enabling few-shot learning on tasks that the model was not specifically trained for. Traditional models achieve breakthrough performance on…

人工智能 · 计算机科学 2025-11-04 Aske Plaat , Annie Wong , Suzan Verberne , Joost Broekens , Niki van Stein , Thomas Back

This study investigates the internal information flow of large language models (LLMs) while performing chain-of-thought (CoT) style reasoning. Specifically, with a particular interest in the faithfulness of the CoT explanation to LLMs'…

Large language models (LLMs) have shown remarkable performances across a wide range of tasks. However, the mechanisms by which these models encode tasks of varying complexities remain poorly understood. In this paper, we explore the…

Large Language Models (LLMs) have shown remarkable performance in various basic natural language tasks. For completing the complex task, we still need a plan for the task to guide LLMs to generate the specific solutions step by step. LLMs…

计算与语言 · 计算机科学 2023-12-14 Yiduo Guo , Yaobo Liang , Chenfei Wu , Wenshan Wu , Dongyan Zhao , Nan Duan

Chain-of-Thought prompting has significantly enhanced the reasoning capabilities of large language models, with numerous studies exploring factors influencing its performance. However, the underlying mechanisms remain poorly understood. To…

人工智能 · 计算机科学 2024-12-06 Hao Yang , Qianghua Zhao , Lei Li

Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the…

计算与语言 · 计算机科学 2026-03-25 Ruidi Chang , Jiawei Zhou , Hanjie Chen

Large Language Models (LLMs) have demonstrated remarkable abilities to solve problems requiring multiple reasoning steps, yet the internal mechanisms enabling such capabilities remain elusive. Unlike existing surveys that primarily focus on…

计算与语言 · 计算机科学 2026-01-22 Liangming Pan , Jason Liang , Jiaran Ye , Minglai Yang , Xinyuan Lu , Fengbin Zhu

Large language models (LLMs) have shown remarkable reasoning capabilities given chain-of-thought prompts (examples with intermediate reasoning steps). Existing benchmarks measure reasoning ability indirectly, by evaluating accuracy on…

计算与语言 · 计算机科学 2023-03-03 Abulhair Saparov , He He

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

计算与语言 · 计算机科学 2025-01-31 Didier Chételat , Joseph Cotnareanu , Rylee Thompson , Yingxue Zhang , Mark Coates

Large Language Models (LLMs) still struggle with multi-step logical reasoning. Existing approaches either purely refine the reasoning chain in natural language form or attach a symbolic solver as an external module. In this work, we instead…

计算与语言 · 计算机科学 2026-04-22 Feihao Fang , My T. Thai , Yuanyuan Lei

This paper delves into the capabilities of large language models (LLMs), specifically focusing on advancing the theoretical comprehension of chain-of-thought prompting. We investigate how LLMs can be effectively induced to generate a…

计算与语言 · 计算机科学 2024-06-07 Rasul Tutunov , Antoine Grosnit , Juliusz Ziomek , Jun Wang , Haitham Bou-Ammar
‹ 上一页 1 2 3 10 下一页 ›