中文
相关论文

相关论文: Can Small Language Models Help Large Language Mode…

200 篇论文

Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short…

人工智能 · 计算机科学 2024-10-22 Ruohong Zhang , Bowen Zhang , Yanghao Li , Haotian Zhang , Zhiqing Sun , Zhe Gan , Yinfei Yang , Ruoming Pang , Yiming Yang

This paper investigates the logical reasoning capabilities of large language models (LLMs). For a precisely defined yet tractable formulation, we choose the conceptually simple but technically complex task of constructing proofs in Boolean…

机器学习 · 计算机科学 2025-04-30 Yuan Xia , Akanksha Atrey , Fadoua Khmaissia , Kedar S. Namjoshi

Large language models (LLMs) equipped with chain-of-thought (CoT) achieve strong performance and offer a window into LLM behavior. However, recent evidence suggests that improvements in CoT capabilities often come with redundant reasoning…

计算与语言 · 计算机科学 2026-02-03 Yanrui Du , Sendong Zhao , Yibo Gao , Danyang Zhao , Qika Lin , Ming Ma , Jiayun Li , Yi Jiang , Kai He , Qianyi Xu , Bing Qin , Mengling Feng

Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances,…

计算与语言 · 计算机科学 2025-10-28 Chenheng Zhang , Tianqi Du , Jizhe Zhang , Mingqing Xiao , Yifei Wang , Yisen Wang , Zhouchen Lin

Large language models (LLMs) can solve problems step-by-step. While this chain-of-thought (CoT) reasoning boosts LLMs' performance, it is unclear if LLMs \textit{know} when to use CoT and whether those CoT are always necessary to answer the…

计算与语言 · 计算机科学 2024-03-21 Cheng-Han Chiang , Hung-yi Lee

While large language models (LLMs) such as ChatGPT and PaLM have demonstrated remarkable performance in various language understanding and generation tasks, their capabilities in complex reasoning and intricate knowledge utilization still…

计算与语言 · 计算机科学 2023-10-11 Haodi Zhang , Min Cai , Xinhe Zhang , Chen Jason Zhang , Rui Mao , Kaishun Wu

Despite rapid advancements in large language models (LLMs), the token-level autoregressive nature constrains their complex reasoning capabilities. To enhance LLM reasoning, inference-time techniques, including…

人工智能 · 计算机科学 2026-01-28 Qianyue Hao , Sibo Li , Jian Yuan , Yong Li

Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by…

计算与语言 · 计算机科学 2024-03-18 Jiashuo Sun , Yi Luo , Yeyun Gong , Chen Lin , Yelong Shen , Jian Guo , Nan Duan

Test-time scaling has enabled Large Language Models (LLMs) to tackle complex reasoning, yet the limitations of current Chain-of-Thought (CoT) evaluation obscures whether performance gains stem from genuine reasoning or mere verbosity. To…

人工智能 · 计算机科学 2026-01-08 Zhizhang Fu , Yuancheng Gu , Chenkai Hu , Hanmeng Liu , Yue Zhang

In recent years, large language models (LLMs) have demonstrated significant potential in complex reasoning tasks like mathematical problem-solving. However, existing research predominantly relies on reinforcement learning (RL) frameworks…

机器学习 · 计算机科学 2026-01-12 ShaoZhen Liu , Xinting Huang , Houwen Peng , Xin Chen , Xinyang Song , Qi Li , Zhenan Sun

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time,…

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 demonstrated potential in predicting mental health outcomes from online text, yet traditional classification methods often lack interpretability and robustness. This study evaluates structured reasoning…

计算与语言 · 计算机科学 2026-01-09 Avinash Patil , Amardeep Kour Gedhu

Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking…

计算与语言 · 计算机科学 2026-03-23 Taiqiang Wu , Zenan Xu , Bo Zhou , Ngai Wong

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

Large Language Models (LLM) exhibit zero-shot mathematical reasoning capacity as a behavior emergent with scale, commonly manifesting as chain-of-thoughts (CoT) reasoning. However, multiple empirical findings suggest that this prowess is…

The advancement of Large Language Models (LLMs) has brought substantial attention to the Chain of Thought (CoT) approach, primarily due to its ability to enhance the capability of LLMs on complex reasoning tasks. Moreover, the significance…

计算与语言 · 计算机科学 2024-03-05 Bingshuai Liu , Chenyang Lyu , Zijun Min , Zhanyu Wang , Jinsong Su , Longyue Wang

Large Language Models (LLMs) struggle with complex reasoning due to limited diversity and inefficient search. We propose Soft Reasoning, an embedding-based search framework that optimises the embedding of the first token to guide…

计算与语言 · 计算机科学 2025-09-16 Qinglin Zhu , Runcong Zhao , Hanqi Yan , Yulan He , Yudong Chen , Lin Gui

Recent advances in Large Language Models (LLMs) have introduced Reasoning Large Language Models (RLLMs), which employ extended thinking processes with reflection and self-correction capabilities, demonstrating the effectiveness of test-time…

人工智能 · 计算机科学 2025-03-26 Yuyao Ge , Shenghua Liu , Yiwei Wang , Lingrui Mei , Lizhe Chen , Baolong Bi , Xueqi Cheng

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes…