中文
相关论文

相关论文: Learning to Correct: Calibrated Reinforcement Lear…

200 篇论文

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…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

计算与语言 · 计算机科学 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen…

人工智能 · 计算机科学 2025-10-31 Guohao Sun , Hang Hua , Jian Wang , Jiebo Luo , Sohail Dianat , Majid Rabbani , Raghuveer Rao , Zhiqiang Tao

Chain-of-thought (CoT) prompting has become central to mathematical reasoning in large language models, yet models remain brittle to early errors: a single arithmetic slip or unjustified inference typically propagates uncorrected to an…

机器学习 · 计算机科学 2025-12-22 Saraswathy Amjith , Mihika Dusad , Neha Muramalla , Shweta Shah

Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on…

The success of Deepseek-R1 has drawn the LLM community's attention to reinforcement learning (RL) methods like GRPO. However, such rule-based 0/1 outcome reward methods lack the capability to regulate the intermediate reasoning processes…

人工智能 · 计算机科学 2025-05-26 Muzhi Dai , Shixuan Liu , Qingyi Si

Recent advances in multimodal Reward Models (RMs) have shown significant promise in delivering reward signals to align vision models with human preferences. However, current RMs are generally restricted to providing direct responses or…

计算机视觉与模式识别 · 计算机科学 2025-10-30 Yibin Wang , Zhimin Li , Yuhang Zang , Chunyu Wang , Qinglin Lu , Cheng Jin , Jiaqi Wang

Scaling inference compute enhances reasoning in large language models (LLMs), with long chains-of-thought (CoTs) enabling strategies like backtracking and error correction. Reinforcement learning (RL) has emerged as a crucial method for…

计算与语言 · 计算机科学 2025-02-06 Edward Yeo , Yuxuan Tong , Morry Niu , Graham Neubig , Xiang Yue

Advanced test-time computing strategies are essential for scaling reasoning models, but their effectiveness is capped by the models' poor self-evaluation. We propose a pairwise Explanatory Verifier, trained via reinforcement learning…

人工智能 · 计算机科学 2025-09-25 Anisha Garg , Engin Tekin , Yash More , David Bick , Nishit Neema , Ganesh Venkatesh

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

Chain-of-Thought (CoT) reasoning typically utilizes the discrete language space for thinking, which is inherently inefficient, as many generated tokens only enforce linguistic rules that are not required for reasoning. To bypass this,…

计算与语言 · 计算机科学 2025-12-16 Enes Özeren , Matthias Aßenmacher

Large Language Models (LLMs) are typically trained to reflect a relatively uniform set of values, which limits their applicability to tasks that require understanding of nuanced human perspectives. Recent research has underscored the…

计算与语言 · 计算机科学 2025-10-07 Yunfan Zhang , Kathleen McKeown , Smaranda Muresan

Reinforcement learning with verifiable reward (RLVR) has been instrumental in eliciting strong reasoning capabilities from large language models (LLMs) via long chains of thought (CoT). During RLVR training, we formalize and systemically…

计算与语言 · 计算机科学 2026-02-24 Cheonbok Park , Jeonghoon Kim , Joosung Lee , Sanghwan Bae , Jaegul Choo , Kang Min Yoo

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

机器学习 · 计算机科学 2025-10-21 Guofu Xie , Yunsheng Shi , Hongtao Tian , Ting Yao , Xiao Zhang

Generating grounded and trustworthy responses remains a key challenge for large language models (LLMs). While retrieval-augmented generation (RAG) with citation-based grounding holds promise, instruction-tuned models frequently fail even in…

计算与语言 · 计算机科学 2025-06-19 Shang Hong Sim , Tej Deep Pala , Vernon Toh , Hai Leong Chieu , Amir Zadeh , Chuan Li , Navonil Majumder , Soujanya Poria

Recent advancements in large language models (LLMs) have been driven by their emergent reasoning capabilities, particularly through long chain-of-thought (CoT) prompting, which enables thorough exploration and deliberation. Despite these…

计算与语言 · 计算机科学 2026-04-09 Junnan Liu , Hongwei Liu , Songyang Zhang , Kai Chen

Chain-of-thought (CoT) reasoning has emerged as a powerful technique for improving the problem-solving capabilities of large language models (LLMs), particularly for tasks requiring multi-step reasoning. However, recent studies show that…

计算与语言 · 计算机科学 2025-12-30 Hadi Mohammadi , Tamas Kozak , Anastasia Giachanou

Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models,…

人工智能 · 计算机科学 2026-05-26 Jingchu Gai , Guanning Zeng , Christina Baek , Chen Wu , J. Zico Kolter , Andrej Risteski , Aditi Raghunathan

Recent advancements in long chain-of-thought (CoT) reasoning, particularly through the Group Relative Policy Optimization algorithm used by DeepSeek-R1, have led to significant interest in the potential of Reinforcement Learning with…

人工智能 · 计算机科学 2025-10-03 Xumeng Wen , Zihan Liu , Shun Zheng , Shengyu Ye , Zhirong Wu , Yang Wang , Zhijian Xu , Xiao Liang , Junjie Li , Ziming Miao , Jiang Bian , Mao Yang

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing Large Language Models (LLMs) on complex reasoning tasks. However, existing methods suffer from an exploration dilemma: the sharply peaked initial…

人工智能 · 计算机科学 2025-09-30 Yuhua Jiang , Jiawei Huang , Yufeng Yuan , Xin Mao , Yu Yue , Qianchuan Zhao , Lin Yan
‹ 上一页 1 2 3 10 下一页 ›