中文
相关论文

相关论文: SynAdapt: Learning Adaptive Reasoning in Large Lan…

200 篇论文

Large language models (LLMs) have demonstrated remarkable capabilities in tasks requiring reasoning and multi-step problem-solving through the use of chain-of-thought (CoT) prompting. However, generating the full CoT process results in…

计算与语言 · 计算机科学 2024-09-16 Tianqiao Liu , Zui Chen , Zitao Liu , Mi Tian , Weiqi Luo

Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer. However, in most cases, the…

计算与语言 · 计算机科学 2024-12-17 Yu Kang , Xianghui Sun , Liangyu Chen , Wei Zou

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…

计算与语言 · 计算机科学 2025-05-28 Yige Xu , Xu Guo , Zhiwei Zeng , Chunyan Miao

Large Language Models (LLMs) have demonstrated remarkable capabilities but often face challenges with tasks requiring sophisticated reasoning. While Chain-of-Thought (CoT) prompting significantly enhances reasoning, it indiscriminately…

机器学习 · 计算机科学 2025-05-27 Chenwei Lou , Zewei Sun , Xinnian Liang , Meng Qu , Wei Shen , Wenqi Wang , Yuntao Li , Qingping Yang , Shuangzhi Wu

The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs). However, despite their widespread adoption and success, CoT methods often exhibit instability…

人工智能 · 计算机科学 2024-09-06 Yu Wang , Shiwan Zhao , Zhihu Wang , Heyuan Huang , Ming Fan , Yubo Zhang , Zhixing Wang , Haijun Wang , Ting Liu

Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require varying depths of reasoning. While some methods can determine…

机器学习 · 计算机科学 2025-11-20 Zhichao Sheng , Shilin Zhou , Chen Gong , Zhenghua Li

Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can significantly increase computational costs, posing challenges for…

计算与语言 · 计算机科学 2025-05-28 Yunhao Wang , Yuhao Zhang , Tinghao Yu , Can Xu , Feng Zhang , Fengzong Lian

Recent advances in large language models (LLMs) have shown that Chain-of-Thought (CoT) reasoning can substantially improve performance on complex reasoning tasks. At the same time, In-Context Learning (ICL) has become an important mechanism…

计算与语言 · 计算机科学 2026-05-19 Rui Chu

Requiring a large language model (LLM) to generate intermediary reasoning steps, known as Chain of Thought (CoT), has been shown to be an effective way of boosting performance. Previous approaches have focused on generating multiple…

计算与语言 · 计算机科学 2025-05-28 Haritz Puerto , Tilek Chubakov , Xiaodan Zhu , Harish Tayyar Madabushi , Iryna Gurevych

Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning methods offer a promising…

计算与语言 · 计算机科学 2026-05-26 Hui Xie , Jie Liu , Ziyue Qiao , Joaquin Vanschore

Long chain-of-thought (CoT) prompting helps Large Language Models (LLMs) solve difficult problems, but very long traces often slow or even degrade performance on fast, intuitive "System-1" tasks. We introduce Connector-Aware Compact CoT…

人工智能 · 计算机科学 2025-09-16 Sunguk Choi , Yonghoon Kwon , Heondeuk Lee

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

Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in real-world reasoning tasks. Nonetheless, the efficacy of a singular, task-level prompt…

计算与语言 · 计算机科学 2024-11-01 Xiaosong Yuan , Chen Shen , Shaotian Yan , Xiaofeng Zhang , Liang Xie , Wenxiao Wang , Renchu Guan , Ying Wang , Jieping Ye

Chain of Thought (CoT) reasoning enhances language models' performance but often leads to inefficient "overthinking" on simple problems. We identify that existing approaches directly penalizing reasoning length fail to account for varying…

计算与语言 · 计算机科学 2025-05-22 Junjie Yang , Ke Lin , Xing Yu

Large language models (LLMs) excel at complex reasoning but can still exhibit harmful behaviors. Current alignment strategies typically embed safety into model weights, making these controls implicit, static, and difficult to modify. This…

计算与语言 · 计算机科学 2025-10-15 Xuanming Zhang , Yuxuan Chen , Samuel Yeh , Sharon Li

Research on LLM technologies is rapidly emerging, with most of them employ a 'fast thinking' approach to inference. Most LLMs generate the final result based solely on a single query and LLM's reasoning capabilities. However, with the…

计算与语言 · 计算机科学 2025-11-14 Jianfeng Pan , Senyou Deng , Shaomang Huang

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…

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging…

计算与语言 · 计算机科学 2025-05-27 Zongqian Wu , Baoduo Xu , Ruochen Cui , Mengmeng Zhan , Xiaofeng Zhu , Lei Feng

Chain-of-thought (CoT) decoding enables language models to improve reasoning performance at the cost of high generation latency in decoding. Recent proposals have explored variants of contemplation tokens, a term we introduce that refers to…

计算与语言 · 计算机科学 2024-12-18 Jeffrey Cheng , Benjamin Van Durme

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet their performance is highly dependent on the prompting strategy and model scale. While reinforcement learning and fine-tuning have been deployed to boost…

人工智能 · 计算机科学 2025-02-10 Tushar Pandey , Ara Ghukasyan , Oktay Goktas , Santosh Kumar Radha
‹ 上一页 1 2 3 10 下一页 ›