AIC CTU系统在AVeriTeC：将自动化事实核查重新构建为简单的RAG任务
AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task
AI总结：
本文提出在AVeriTeC共享任务中利用简单RAG方案解决事实核查挑战，设计检索器与证据标签生成器模块，采用GPT-4o实现第三名成绩，并通过错误分析指出数据噪声问题。
摘要：
本文描述了我们在AVeriTeC共享任务中获得第3名的提交方案。在该任务中，我们试图利用大型语言模型的预测能力，通过为该任务设计的检索增强生成（RAG）简单方案，解决在开放环境中检索证据进行事实核查的挑战。我们发布了代码库，并详细解释了其两个模块——检索器和证据与标签生成器，论证了MMR重排序和Likert量表置信度估计等特性。我们在AVeriTeC开发集和测试集上评估了解决方案并解释了结果，选择GPT-4o作为发布时我们流水线中最合适的模型，而Llama 3.1 70B是有前景的开源替代方案。我们进行了经验性错误分析，发现预测中的错误常与数据噪声或模糊的事实核查相吻合，这促使进一步研究和数据增强。
英文摘要：
This paper describes our $3^{rd}$ place submission in the AVeriTeC shared task in which we attempted to address the challenge of fact-checking with evidence retrieved in the wild using a simple scheme of Retrieval-Augmented Generation (RAG) designed for the task, leveraging the predictive power of Large Language Models. We release our codebase and explain its two modules - the Retriever and the Evidence & Label generator - in detail, justifying their features such as MMR-reranking and Likert-scale confidence estimation. We evaluate our solution on AVeriTeC dev and test set and interpret the results, picking the GPT-4o as the most appropriate model for our pipeline at the time of our publication, with Llama 3.1 70B being a promising open-source alternative. We perform an empirical error analysis to see that faults in our predictions often coincide with noise in the data or ambiguous fact-checks, provoking further research and data augmentation.
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。
