通过指代消解提升大模型对长文本的理解与问答能力
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
- 设计针对长文本的指代消解框架，分步处理指代关系
- 在多个模型和数据集上显著提升问答准确率，尤其在GPT-4o上表现突出
- 适合需要处理复杂长文档的应用场景，如法律、科研文本理解
大语言模型在自然语言处理中展现出强大能力，但在理解和回答长篇文本时仍面临挑战，主要源于文本的复杂性和歧义性。为提升模型在长上下文中的表现，我们提出长问题指代消解适配（LQCA）方法。该框架针对长文本特点优化指代消解，包含四个步骤：子文档内指代消解、提及项间距离计算、代表性提及定义以及通过提及替换进行问答。系统化处理使模型能更有效地解析长文本。在多种LLM和数据集上的实验表明，该方法在OpenAI-o1-mini和GPT-4o模型上均取得显著性能提升，验证了利用指代消解弥合上下文差距的有效性。代码已开源。
原文摘要 · Abstract (English)
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 answering. These challenges often arise due to the complexity and ambiguity present in longer texts. To enhance the performance of LLMs in such scenarios, we introduce the Long Question Coreference Adaptation (LQCA) method. This innovative framework focuses on coreference resolution tailored to long contexts, allowing the model to identify and manage references effectively. The LQCA method encompasses four key steps: resolving coreferences within sub-documents, computing the distances between mentions, defining a representative mention for coreference, and answering questions through mention replacement. By processing information systematically, the framework provides easier-to-handle partitions for LLMs, promoting better understanding. Experimental evaluations on a range of LLMs and datasets have yielded positive results, with a notable improvements on OpenAI-o1-mini and GPT-4o models, highlighting the effectiveness of leveraging coreference resolution to bridge context gaps in question answering. Our code is public at https://github.com/OceannTwT/LQCA.
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。