5 papers
GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning
Ningyuan Yang, Weihua Du, Weiwei Sun +2
Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problem…
Deep Research: A Systematic Survey
Zhengliang Shi, Yiqun Chen, Haitao Li +23
Large language models (LLMs) have rapidly evolved from text generators into powerful problem solvers. Yet, many open tasks demand critical thinking, multi-source, and verifiable ou…
ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
Weiwei Sun, Keyi Kong, Xinyu Ma +5
Generative retrieval (GR) reformulates information retrieval (IR) by framing it as the generation of document identifiers (docids), thereby enabling end-to-end optimization and sea…
Enhancing Training Data Attribution with Representational Optimization
Weiwei Sun, Haokun Liu, Nikhil Kandpal +2
Training data attribution (TDA) methods aim to measure how training data impacts a model's predictions. While gradient-based attribution methods, such as influence functions, offer…
Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
Yiqun Chen, Lingyong Yan, Weiwei Sun +6
Retrieval-augmented generation (RAG) is widely utilized to incorporate external knowledge into large language models, thereby enhancing factuality and reducing hallucinations in qu…