ACL

MMUIE: Massive Multi-Domain Universal Information Extraction for Long Documents

Are the Values of LLMs Structurally Aligned with Humans?A Causal Perspective

Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection

LangSuit⋅E: Controlling, Planning, and Interacting with Large Language Models in Embodied Text Environments

Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels

Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling