4 papers
Learning to Generate and Extract: A Multi-Agent Collaboration Framework For Zero-shot Document-level Event Arguments Extraction
Guangjun Zhang, Hu Zhang, Yazhou Han +4
Document-level event argument extraction (DEAE) is essential for knowledge acquisition, aiming to extract participants of events from documents . In the zero-shot setting, existing…
Uncovering and Mitigating Transient Blindness in Multimodal Model Editing
Xiaoqi Han, Ru Li, Ran Yi +4
Multimodal Model Editing (MMED) aims to correct erroneous knowledge in multimodal models. Existing evaluation methods, adapted from textual model editing, overstate success by rely…
Memorization Understanding: Do Large Language Models Have the Ability of Scenario Cognition?
Boxiang Ma, Ru Li, Yuanlong Wang +2
Driven by vast and diverse textual data, large language models (LLMs) have demonstrated impressive performance across numerous natural language processing (NLP) tasks. Yet, a criti…
Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities
Zhichao Yan, Jiapu Wang, Jiaoyan Chen +6
Retrieval-Augmented Generation (RAG) shows impressive performance by supplementing and substituting parametric knowledge in Large Language Models (LLMs). Retrieved knowledge can be…