中文
相关论文

相关论文: HS-STaR: Hierarchical Sampling for Self-Taught Rea…

200 篇论文

Large language models (LLMs) inevitably make mistakes when performing step-by-step mathematical reasoning. Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step. However, existing PRMs typically…

计算与语言 · 计算机科学 2025-03-28 Shuaijie She , Junxiao Liu , Yifeng Liu , Jiajun Chen , Xin Huang , Shujian Huang

Large Language Models (LLMs) are increasingly applied to complex tasks that require extended reasoning. In such settings, models often benefit from diverse chains-of-thought to arrive at multiple candidate solutions. This requires two…

机器学习 · 计算机科学 2025-10-08 Xueyan Li , Guinan Su , Mrinmaya Sachan , Jonas Geiping

Large language models (LLMs) are predominantly used as evaluators for natural language generation (NLG) tasks, but their application to broader evaluation scenarios remains limited. In this work, we explore the potential of LLMs as general…

人工智能 · 计算机科学 2025-12-02 Jie Meng , Jin Mao

The evolution of Large Language Models (LLMs) is shifting the focus from single, verifiable tasks toward complex, open-ended real-world scenarios, imposing significant challenges on the post-training phase. In these settings, the scale and…

Process Reward Models (PRMs) provide step-level supervision that improves the reliability of reasoning in large language models. While PRMs have been extensively studied in text-based domains, their extension to Vision Language Models…

人工智能 · 计算机科学 2025-10-08 Brandon Ong , Tej Deep Pala , Vernon Toh , William Chandra Tjhi , Soujanya Poria

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

机器学习 · 计算机科学 2025-10-21 Mengqi Liao , Xiangyu Xi , Ruinian Chen , Jia Leng , Yangen Hu , Ke Zeng , Shuai Liu , Huaiyu Wan

Considering the challenges faced by large language models (LLMs) in logical reasoning and planning, prior efforts have sought to augment LLMs with access to external solvers. While progress has been made on simple reasoning problems,…

计算与语言 · 计算机科学 2025-11-11 Yu Zhang , Hui-Ling Zhen , Zehua Pei , Yingzhao Lian , Lihao Yin , Mingxuan Yuan , Bei Yu

Large language models (LLMs) are increasingly evaluated on reasoning tasks, yet their logical abilities remain contested. To address this, we study LLMs' reasoning in a well-defined fragment of logic: syllogistic reasoning. We cast the…

计算与语言 · 计算机科学 2026-01-27 Leonardo Bertolazzi , Manuel Vargas Guzmán , Raffaella Bernardi , Maciej Malicki , Jakub Szymanik

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

机器学习 · 计算机科学 2026-01-07 Tuc Nguyen , Thai Le

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…

人工智能 · 计算机科学 2026-05-26 Yanyu Chen , Jiyue Jiang , Dianzhi Yu , Zheng Wu , Jiahong Liu , Jiaming Han , Xiao Guo , Jinhu Qi , Yu Li , Yifei Zhang , Irwin King

Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based,…

计算与语言 · 计算机科学 2025-06-06 Ho-Lam Chung , Teng-Yun Hsiao , Hsiao-Ying Huang , Chunerh Cho , Jian-Ren Lin , Zhang Ziwei , Yun-Nung Chen

Recent advancements have significantly enhanced the performance of large language models (LLMs) in tackling complex reasoning tasks, achieving notable success in domains like mathematical and logical reasoning. However, these methods…

人工智能 · 计算机科学 2025-05-30 Runquan Gui , Zhihai Wang , Jie Wang , Chi Ma , Huiling Zhen , Mingxuan Yuan , Jianye Hao , Defu Lian , Enhong Chen , Feng Wu

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For…

人工智能 · 计算机科学 2025-10-30 Tianqianjin Lin , Xi Zhao , Xingyao Zhang , Rujiao Long , Yi Xu , Zhuoren Jiang , Wenbo Su , Bo Zheng

We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's…

计算与语言 · 计算机科学 2025-05-27 Junnan Liu , Hongwei Liu , Linchen Xiao , Shudong Liu , Taolin Zhang , Zihan Ma , Songyang Zhang , Kai Chen

While large language models (LLMs) demonstrate emerging reasoning capabilities, current inference-time expansion methods incur prohibitive computational costs by exhaustive sampling. Through analyzing decoding trajectories, we observe that…

人工智能 · 计算机科学 2026-02-03 Ziheng Li , Hengyi Cai , Xiaochi Wei , Yuchen Li , Shuaiqiang Wang , Zhi-Hong Deng , Dawei Yin

Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning…

计算与语言 · 计算机科学 2025-07-17 Yanjian Zhang , Guillaume Wisniewski , Nadi Tomeh , Thierry Charnois

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

机器学习 · 计算机科学 2026-03-24 Yuanfu Wang , Zhixuan Liu , Xiangtian Li , Chaochao Lu , Chao Yang

Logical rules, both transferable and explainable, are widely used as weakly supervised signals for many downstream tasks such as named entity tagging. To reduce the human effort of writing rules, previous researchers adopt an iterative…

计算与语言 · 计算机科学 2022-10-07 Tao Chen , Luxin Liu , Xuepeng Jia , Baoliang Cui , Haihong Tang , Siliang Tang

Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Sourabh Sharma , Sonam Gupta , Sadbhawna

While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…

计算与语言 · 计算机科学 2025-05-28 Yang He , Xiao Ding , Bibo Cai , Yufei Zhang , Kai Xiong , Zhouhao Sun , Bing Qin , Ting Liu
‹ 上一页 1 8 9 10 下一页 ›