activity
20232026
most citedGRACE: Generative Representation Learning via Contrastive Policy Optimization

1 citations · 4 across the 20 of their papers we have counts for

collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL2026

EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering

Xuanyu Meng, Jiashuo Sun, Jash Rajesh Parekh +1

Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multiple entities and their relationships. Existing retrieval-augmente…

cs.CL2026

TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation

Jiashuo Sun, Yixuan Xie, Jimeng Shi +2

Retrieval-Augmented Generation (RAG) helps large language models (LLMs) answer knowledge-intensive and time-sensitive questions by conditioning generation on external evidence. How…

cs.CL2026

Learning to Predict Future-Aligned Research Proposals with Language Models

Heng Wang, Pengcheng Jiang, Jiashuo Sun +4

Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and sou…

cs.CL2026

Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation

Jiashuo Sun, Pengcheng Jiang, Saizhuo Wang +13

Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-K results. A key reason is that retr…

cs.CL2025

Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning

Junlin Wu, Xianrui Zhong, Jiashuo Sun +4

Large language models (LLMs) have demonstrated remarkable advances in reasoning capabilities. However, their performance remains constrained by limited access to explicit and struc…

cs.CL20251 cited

GRACE: Generative Representation Learning via Contrastive Policy Optimization

Jiashuo Sun, Shixuan Liu, Zhaochen Su +6

Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and…