11 papers
ForestBench: A Unified Graph Framework for Evaluating Multi-Agent Collaboration
Guo Chen, Ziwen Li, Reed Li +4
Multi-agent systems (MAS) built on Large Language Models (LLMs) are proliferating rapidly, but their heterogeneous execution traces provide no common basis for evaluation across me…
NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation
Guo Chen, Ziwen Li, Maolin Zheng +3
The paper proposes NGM-RAG, a framework that combines graph neural networks with text matching to improve retrieval-augmented generation for tasks requiring multi-hop reasoning and…
The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates
Shaobo Wang, Guo Chen, Ziyue Wang +5
With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The challenge is that base pre-…
VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding
Shihao Wang, Guo Chen, De-an Huang +6
While Video Large Language Models (Video-LLMs) have shown significant potential in multimodal understanding and reasoning tasks, how to efficiently select the most informative fram…
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Shaobo Wang, Xuan Ouyang, Tianyi Xu +9
As high-quality public text approaches exhaustion, a phenomenon known as the Data Wall, pre-training is shifting from more tokens to better tokens. However, existing methods either…
Grounding and Enhancing Informativeness and Utility in Dataset Distillation
Shaobo Wang, Yantai Yang, Guo Chen +5
Dataset Distillation (DD) seeks to create a compact dataset from a large, real-world dataset. While recent methods often rely on heuristic approaches to balance efficiency and qual…