中文
相关论文

相关论文: NaturalThoughts: Selecting and Distilling Reasonin…

200 篇论文

Uncertainty quantification for LLMs is a key research direction towards addressing hallucination and other issues that limit their reliable deployment. In this work, we show that reasoning trace length is a simple and useful confidence…

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of Large Language Models (LLMs). However, these methods often suffer from overthinking, leading to unnecessarily lengthy or redundant…

计算与语言 · 计算机科学 2025-06-13 Zhensheng Jin , Xinze Li , Yifan Ji , Chunyi Peng , Zhenghao Liu , Qi Shi , Yukun Yan , Shuo Wang , Furong Peng , Ge Yu

Large language models have emerged as powerful tools for general intelligence, showcasing advanced natural language processing capabilities that find applications across diverse domains. Despite their impressive performance, recent studies…

计算与语言 · 计算机科学 2025-04-01 Elita Lobo , Chirag Agarwal , Himabindu Lakkaraju

Large language models (LLMs) have achieved remarkable advancements in natural language processing. However, the massive scale and computational demands of these models present formidable challenges when considering their practical…

计算与语言 · 计算机科学 2024-04-09 Weize Liu , Guocong Li , Kai Zhang , Bang Du , Qiyuan Chen , Xuming Hu , Hongxia Xu , Jintai Chen , Jian Wu

Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and…

人工智能 · 计算机科学 2026-04-28 Guangxiang Zhao , Qilong Shi , Xusen Xiao , Xiangzheng Zhang , Tong Yang , Lin Sun

Recently, scaling test-time compute on Large Language Models (LLM) has garnered wide attention. However, there has been limited investigation of how various reasoning prompting strategies perform as scaling. In this paper, we focus on a…

人工智能 · 计算机科学 2025-08-18 Yexiang Liu , Zekun Li , Zhi Fang , Nan Xu , Ran He , Tieniu Tan

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. Recent advancements in Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have further improved performance in System-2 reasoning…

Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…

计算与语言 · 计算机科学 2024-11-27 Tim Hartill

Chain-of-thought emerges as a promising technique for eliciting reasoning capabilities from Large Language Models (LLMs). However, it does not always improve task performance or accurately represent reasoning processes, leaving unresolved…

计算与语言 · 计算机科学 2024-12-13 Guangsheng Bao , Hongbo Zhang , Cunxiang Wang , Linyi Yang , Yue Zhang

Large language models (LLMs) have shown promising self-correction abilities, where iterative refinement improves the quality of generated responses. However, most existing approaches operate at the level of output critique, patching surface…

人工智能 · 计算机科学 2026-02-03 Hossein A. Rahmani , Mengting Wan , Pei Zhou , Longqi Yang , Nick Craswell , Emine Yilmaz , Sujay Kumar Jauhar

Large language models have recently demonstrated significant gains in reasoning ability, often attributed to their capacity to generate longer chains of thought and engage in reflective reasoning. However, the contribution of reflections to…

人工智能 · 计算机科学 2025-10-10 Liwei Kang , Yue Deng , Yao Xiao , Zhanfeng Mo , Wee Sun Lee , Lidong Bing

Language models (LMs) have yielded impressive results on many language reasoning tasks, but their unexpected errors raise doubts about their reasoning abilities. In light of this, there is growing interest in finetuning/prompting LMs with…

计算与语言 · 计算机科学 2023-05-23 Aaron Chan , Zhiyuan Zeng , Wyatt Lake , Brihi Joshi , Hanjie Chen , Xiang Ren

Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on either reinforcement learning (RL) with verifiable signals or supervised…

计算与语言 · 计算机科学 2026-03-17 Yige Yuan , Teng Xiao , Shuchang Tao , Xue Wang , Jinyang Gao , Bolin Ding , Bingbing Xu

Large Language Models (LLMs) have transformed the natural language processing landscape and brought to life diverse applications. Pretraining on vast web-scale data has laid the foundation for these models, yet the research community is now…

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

Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their…

人工智能 · 计算机科学 2025-11-21 Parshin Shojaee , Iman Mirzadeh , Keivan Alizadeh , Maxwell Horton , Samy Bengio , Mehrdad Farajtabar

In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understanding and advanced reasoning capabilities. However,…

信息检索 · 计算机科学 2025-09-22 Haowei Liu , Xuyang Wu , Guohao Sun , Zhiqiang Tao , Yi Fang

Investigating the reasoning abilities of transformer models, and discovering new challenging tasks for them, has been a topic of much interest. Recent studies have found these models to be surprisingly strong at performing deductive…

计算与语言 · 计算机科学 2021-12-17 Kyle Richardson , Ashish Sabharwal

Large language models (LLMs) have a substantial capacity for high-level analogical reasoning: reproducing patterns in linear text that occur in their training data (zero-shot evaluation) or in the provided context (few-shot in-context…

计算与语言 · 计算机科学 2023-06-05 Batu Ozturkler , Nikolay Malkin , Zhen Wang , Nebojsa Jojic

Large Language Models (LLMs) with reasoning capabilities have achieved state-of-the-art performance on a wide range of tasks. Despite its empirical success, the tasks and model scales at which reasoning becomes effective, as well as its…

计算与语言 · 计算机科学 2025-09-29 Nicolas Boizard , Hippolyte Gisserot-Boukhlef , Kevin El-Haddad , Céline Hudelot , Pierre Colombo