Improving LLMs' Learning for Coreference Resolution
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Coreference ResolutionSimilar Papers 제목 키워드 기반
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answe…
coreference-resolutionCoreference ResolutionQuestion AnsweringWhat GPT Knows About Who is Who
Coreference resolution -- which is a crucial task for understanding discourse and language at large -- has yet to witness widespread benefits from large language models (LLMs). Moreover, coreference resolution systems la…
coreference-resolutionCoreference ResolutionPrompt EngineeringvalidLegalCore: A Dataset for Legal Documents Event Coreference Resolution
Recognizing events and their coreferential mentions in a document is essential for understanding semantic meanings of text. The existing research on event coreference resolution is mostly limited to news articles. In thi…
Articlescoreference-resolutionCoreference ResolutionEvent Coreference Resolution+1BioCoref: Benchmarking Biomedical Coreference Resolution with LLMs
Coreference resolution in biomedical texts presents unique challenges due to complex domain-specific terminology, high ambiguity in mention forms, and long-distance dependencies between coreferring expressions. In this w…
Coreference ResolutionPrompt EngineeringCorrect-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs
Large Language Models (LLMs) are intended to reflect human linguistic competencies. But humans have access to a broad and embodied context, which is key in detecting and resolving linguistic ambiguities, even in isolated…
Coreference Resolution