解决大模型共指消解中的幻觉与性能不足问题。
Improving LLMs' Learning for Coreference Resolution
- 反向训练结合联合推理，提升问答模板效果。
- 迭代文档生成消除生成文本幻觉，提升消解准确率。
- 适合需要高精度共指消解的NLP应用开发。
共指消解（CR）对众多自然语言处理任务至关重要，但现有大模型在该任务上存在幻觉和性能不足的问题。本文研究了基于大模型的共指消解方法——特别是问答模板（QA Template）与文档模板（Document Template）的局限性，并提出两种新方法：反向训练结合联合推理，以及迭代文档生成。实验表明，反向训练能有效提升问答模板的表现，而迭代文档生成可彻底消除生成文本中的幻觉，并显著提升共指消解性能。将两者结合可为大模型驱动的共指消解提供一种高效且稳健的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。