Improving LLMs' Learning for Coreference Resolution
This addresses coreference resolution for NLP tasks, but appears incremental as it builds on existing LLM-based methods.
The paper tackled the problem of LLMs struggling with hallucination and under-performance in Coreference Resolution by proposing Reversed Training with Joint Inference and Iterative Document Generation, which improved the QA Template method and eliminated hallucinations in generated text.
Coreference Resolution (CR) is crucial for many NLP tasks, but existing LLMs struggle with hallucination and under-performance. In this paper, we investigate the limitations of existing LLM-based approaches to CR-specifically the Question-Answering (QA) Template and Document Template methods and propose two novel techniques: Reversed Training with Joint Inference and Iterative Document Generation. Our experiments show that Reversed Training improves the QA Template method, while Iterative Document Generation eliminates hallucinations in the generated source text and boosts coreference resolution. Integrating these methods and techniques offers an effective and robust solution to LLM-based coreference resolution.