English
Related papers

Related papers: Distill and Align Decomposition for Enhanced Claim…

200 papers

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Jing Wang , Jiajun Liang , Jie Liu , Henglin Liu , Gongye Liu , Jun Zheng , Wanyuan Pang , Ao Ma , Zhenyu Xie , Xintao Wang , Meng Wang , Pengfei Wan , Xiaodan Liang

Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization. Furthermore, a key use case of…

Machine Learning · Computer Science 2025-10-30 Edoardo Cetin , Tianyu Zhao , Yujin Tang

Diffusion large language models (dLLMs), which offer a promising alternative to traditional autoregressive LLMs, have recently shown strong results in pretraining. However, due to their lack of tractable sequence-level likelihoods, they…

Machine Learning · Computer Science 2026-02-03 Anthony Zhan

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods…

Recent advancements in flow-matching have enabled high-quality text-to-image generation. However, the deterministic nature of flow-matching models makes them poorly suited for reinforcement learning, a key tool for improving image quality…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Benjamin Yu , Jackie Liu , Justin Cui

Current Text-to-SQL methods are evaluated and only focused on executable queries, overlooking the semantic alignment challenge -- both in terms of the semantic meaning of the query and the correctness of the execution results. Even…

Computation and Language · Computer Science 2025-11-24 Ashish Kattamuri , Ishita Prasad , Meetu Malhotra , Arpita Vats , Rahul Raja , Albert Lie

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

Information Retrieval · Computer Science 2025-04-15 Pengcheng Jiang , Jiacheng Lin , Lang Cao , Runchu Tian , SeongKu Kang , Zifeng Wang , Jimeng Sun , Jiawei Han

A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL. However, existing works heavily rely on the purity of the data,…

Machine Learning · Computer Science 2022-10-20 Chengqian Gao , Ke Xu , Liu Liu , Deheng Ye , Peilin Zhao , Zhiqiang Xu

The goal of reinforcement learning (RL) is to find a policy that maximizes the expected cumulative return. It has been shown that this objective can be represented as an optimization problem of state-action visitation distribution under…

Machine Learning · Computer Science 2024-01-29 Harshit Sikchi , Qinqing Zheng , Amy Zhang , Scott Niekum

The CLIP model has established itself as a cornerstone of large-scale retrieval systems. However, its performance often degrades under distributional shifts such as multilingual, long-form, or multimodal queries. To avoid the prohibitive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Zhaohua Zhang , Jianhuan Zhuo , Muxi Chen , Chenchen Zhao , Wenyu Jiang , Tianwen Jiang , Mingyang Chen , Yutang , Qiuyong Xiao , Jihong Zhang , Zhixun Su

Prevalent reinforcement learning~(RL) methods for fine-tuning LLM reasoners, such as GRPO or Leave-one-out PPO, abandon the learned value function in favor of empirically estimated returns. This hinders test-time compute scaling that relies…

Machine Learning · Computer Science 2026-04-14 Kusha Sareen , Morgane M Moss , Alessandro Sordoni , Rishabh Agarwal , Arian Hosseini

Retrieval-Augmented Generation (RAG) expands the knowledge of Large Language Models (LLMs), yet current static retrieval methods struggle with complex, multi-hop problems. While recent dynamic retrieval strategies offer improvements, they…

Computation and Language · Computer Science 2026-04-23 Haijian Liang , Zenghao Niu , Junjie Wu , Changwang Zhang , Wangchunshu Zhou , Jun Wang

Recent advances in reinforcement learning (RL) have significantly enhanced the reasoning capabilities of large language models (LLMs). Group Relative Policy Optimization (GRPO), a lightweight variant of Proximal Policy Optimization (PPO),…

Machine Learning · Computer Science 2025-10-13 Chen Wang , Lai Wei , Yanzhi Zhang , Chenyang Shao , Zedong Dan , Weiran Huang , Yuzhi Zhang , Yue Wang

Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relative Policy Optimization (GRPO). However, GRPO frequently suffers from…

Artificial Intelligence · Computer Science 2026-02-09 Yu Zhao , Fan Jiang , Tianle Liu , Bo Zeng , Yu Liu , Longyue Wang , Weihua Luo

Fact verification aims to verify a claim using evidence from a trustworthy knowledge base. To address this challenge, algorithms must produce features for every claim that are both semantically meaningful, and compact enough to find a…

Computation and Language · Computer Science 2024-03-08 Adrián Bazaga , Pietro Liò , Gos Micklem

E-commerce platforms and payment solution providers face increasingly sophisticated fraud schemes, ranging from identity theft and account takeovers to complex money laundering operations that exploit the speed and anonymity of digital…

Artificial Intelligence · Computer Science 2026-01-12 Cooper Lin , Yanting Zhang , Maohao Ran , Wei Xue , Hongwei Fan , Yibo Xu , Zhenglin Wan , Sirui Han , Yike Guo , Jun Song

LLM developers are increasingly reliant on synthetic data, but generating high-quality data for complex long-context reasoning tasks remains challenging. We introduce CLIPPER, a compression-based approach for generating synthetic data…

Computation and Language · Computer Science 2025-08-06 Chau Minh Pham , Yapei Chang , Mohit Iyyer

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with…

Computation and Language · Computer Science 2025-07-29 Songjun Tu , Jiahao Lin , Xiangyu Tian , Qichao Zhang , Linjing Li , Yuqian Fu , Nan Xu , Wei He , Xiangyuan Lan , Dongmei Jiang , Dongbin Zhao

RAG systems are increasingly deployed in high-stakes domains where users expect outputs to be consistent across semantically equivalent queries. However, existing systems often exhibit significant inconsistencies due to variability in both…

Computation and Language · Computer Science 2025-10-07 Faisal Hamman , Chenyang Zhu , Anoop Kumar , Xujun Peng , Sanghamitra Dutta , Daben Liu , Alfy Samuel

Large Language Models (LLMs) have been increasingly employed for query expansion. However, their generative nature often undermines performance on complex multi-hop retrieval tasks by introducing irrelevant or noisy information. To address…

Information Retrieval · Computer Science 2026-03-24 JungMin Yun , YoungBin Kim