news

Aug 21, 2025 Our three paper “Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs”, “Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks”, and “Adaptive Preference Optimization with Uncertainty-aware Utility Anchor” were accepted to the Main Conference and Findings of EMNLP 2025!
May 16, 2025 Our two paper Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training and Reflectevo: Improving meta introspection of small llms by learning self-reflection were accepted to the Main Conference and Findings of ACL 2025!
Feb 17, 2025 Our one paper From hours to minutes: Lossless acceleration of ultra long sequence generation up to 100k tokens was accepted to the ICML 2025!
May 17, 2024 Our short paper Varying Sentence Representations via Condition-Specified Routers was accepted to the Main Conference of EMNLP 2024!
May 17, 2024 Our paper Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels was accepted to the Main Conference of ACL 2024!
May 17, 2024 Our paper LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments was accepted to the ACL 2024 Findings!
Jul 18, 2023 Our paper A Unified Retrieval-augmented System for Multilingual Named Entity Recognition wins the Best System Paper Award at SemEval 2023! :sparkles: :smile:
May 17, 2023 Our short paper Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models was accepted to the Main Conference of EMNLP 2023!
May 5, 2023 Our paper Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field was accepted to the Main Conference of ACL 2023!