通过基于实体幻觉指数的强化学习减少摘要生成中的幻觉
Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index
AI总结：
针对抽象式摘要的幻觉问题，提出基于实体幻觉指数（EHI）的强化学习微调框架，无需人工事实标注即可提升摘要实体忠实度，且不损害流畅度与信息量，同时开源了可复现实验流程。
摘要：
在抽象式摘要生成中减少幻觉，仍是语言模型（LM）落地部署时的一项关键挑战。本研究提出了一种奖励驱动的微调框架，该框架针对实体幻觉指数（Entity Hallucination Index，EHI）进行显式优化——EHI是一种用于量化生成摘要中命名实体的存在性、正确性及事实支撑性的指标。针对一组会议转录语料，我们首先使用预训练LM生成基线摘要，并通过自动实体提取与匹配计算EHI分数。随后我们采用强化学习微调模型参数，将EHI作为奖励信号，引导生成结果偏向实体忠实的输出。该方法无需人工撰写的事实性标注，可实现可扩展的微调。实验表明，该方法在多个数据集上的EHI均有持续提升，定性分析显示实体级幻觉显著减少，且流畅度与信息量未出现下降。我们还发布了可复现的Colab流程，为使用EHI这类轻量级幻觉指标开展幻觉感知模型微调的后续研究提供便利。
英文摘要：
Reducing hallucinations in abstractive summarization remains a critical challenge for deploying language models (LMs) in real-world settings. In this work, we introduce a rewarddriven fine-tuning framework that explicitly optimizes for Entity Hallucination Index (EHI), a metric designed to quantify the presence, correctness, and grounding of named entities in generated summaries. Given a corpus of meeting transcripts, we first generate baseline summaries using a pre-trained LM and compute EHI scores via automatic entity extraction and matching. We then apply reinforcement learning to fine-tune the model parameters, using EHI as a reward signal to bias generation toward entity-faithful outputs. Our approach does not rely on human-written factuality annotations, enabling scalable fine-tuning. Experiments demonstrate consistent improvements in EHI across datasets, with qualitative analysis revealing a significant reduction in entity-level hallucinations without degradation in fluency or informativeness. We release a reproducible Colab pipeline, facilitating further research on hallucination-aware model fine-tuning using lightweight, hallucintion metrics like EHI.
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。
