1

Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents
Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement
WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning
DocRED-FE: A Document-Level Fine-Grained Entity and Relation Extraction Dataset
A Transition-based Method for Complex Question Understanding
ConFiguRe: Exploring Discourse-level Chinese Figures of Speech
IntTower: the Next Generation of Two-Tower Model for Pre-Ranking System