基于遵循指令的LLM的零样本和少样本学习在自动事实核查中的声明匹配应用
Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking
AI总结：
本研究首次探索基于遵循指令的LLM的零样本和少样本学习方法，通过将其视为二分类任务并利用自然语言推理等成熟任务，解决自动事实核查中的声明匹配问题，同时发布了新数据集ClaimMatch及评估流程。
摘要：
声明匹配（CM）任务通过将可用同一事实核查解决的声明归拢在一起，能使自动事实核查流程受益。本研究首次探索了该任务的零样本和少样本学习方法。我们将CM视为二分类任务，并实验了一组遵循指令的大型语言模型（GPT-3.5-turbo、Gemini-1.5-flash、Mistral-7B-Instruct和Llama-3-8B-Instruct），研究了提示模板。我们引入了新的CM数据集ClaimMatch，将在论文被接收后发布。我们在CM任务中测试了LLM，发现可通过利用更成熟且相似的任务（如自然语言推理或复述检测）来解决该问题。我们还提出了一种CM流程，并在不同长度的文本上进行了评估。
英文摘要：
The claim matching (CM) task can benefit an automated fact-checking pipeline by putting together claims that can be resolved with the same fact-check. In this work, we are the first to explore zero-shot and few-shot learning approaches to the task. We consider CM as a binary classification task and experiment with a set of instruction-following large language models (GPT-3.5-turbo, Gemini-1.5-flash, Mistral-7B-Instruct, and Llama-3-8B-Instruct), investigating prompt templates. We introduce a new CM dataset, ClaimMatch, which will be released upon acceptance. We put LLMs to the test in the CM task and find that it can be tackled by leveraging more mature yet similar tasks such as natural language inference or paraphrase detection. We also propose a pipeline for CM, which we evaluate on texts of different lengths.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
