用大模型生成的细粒度反馈训练摘要事实验证模型，效果更好更省钱。
Learning to Verify Summary Facts with Fine-Grained LLM Feedback
- 用10个大模型生成摘要，再用Llama-3-70B提供细粒度反馈
- 在人类测试集上，基于大模型数据训练的模型表现优于人工标注数据
- 适合想低成本训练事实验证模型的研究者和工程师
自动摘要事实验证的训练常受限于人工标注数据不足。本文提出一种替代方案：利用大语言模型（LLM）生成的反馈来弥补这一缺陷。我们构建了FineSumFact，一个大规模细粒度事实反馈摘要数据集，使用10种不同LLM生成摘要，并由Llama-3-70B-Instruct提供反馈。在此数据集上，我们微调了轻量级开源模型Llama-3-8B-Instruct，以实现资源高效与高性能的平衡。实验表明，在人类生成的测试集上，基于大规模LLM生成数据训练的模型表现优于基于小规模人工标注数据训练的模型。这说明使用大模型反馈进行微调，比依赖人工反馈更有效且更具成本效益。数据集已公开于https://github.com/DISL-Lab/FineSumFact。
原文摘要 · Abstract (English)
Training automatic summary fact verifiers often faces the challenge of a lack of human-labeled data. In this paper, we explore alternative way of leveraging Large Language Model (LLM) generated feedback to address the inherent limitation of using human-labeled data. We introduce FineSumFact, a large-scale dataset containing fine-grained factual feedback on summaries. We employ 10 distinct LLMs for diverse summary generation and Llama-3-70B-Instruct for feedback. We utilize this dataset to fine-tune the lightweight open-source model Llama-3-8B-Instruct, optimizing resource efficiency while maintaining high performance. Our experimental results reveal that the model trained on extensive LLM-generated datasets surpasses that trained on smaller human-annotated datasets when evaluated using human-generated test sets. Fine-tuning fact verification models with LLM feedback can be more effective and cost-efficient than using human feedback. The dataset is available at https://github.com/DISL-Lab/FineSumFact.
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。