LoVeC：强化学习用于长文生成中的更可靠的 verbalized 自信度
LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations
AI总结：
本文提出LoVeC，一种基于强化学习的方法，通过在长文生成过程中实时附加数值自信度评分，提升事实性生成的可靠性。实验表明，该方法在多个长文问答数据集上实现了更好的校准和跨领域泛化能力，且效率显著高于传统自一致性方法。
摘要：
hallucination仍然是大型语言模型（LLMs）在事实性内容生成中安全可靠部署的主要挑战。先前工作探索了置信度估计作为检测hallucination的有效方法，但通常依赖于计算成本高的事后自一致性方法。verbalized置信度提供了一种更高效的替代方案，但现有方法大多局限于短文问答任务，难以推广到开放性生成。本文提出LoVeC（Long-form Verbalized Confidence），一种新的基于强化学习的方法，训练LLMs在长文生成过程中实时附加数值置信度评分。置信度评分作为直接且可解释的事实性生成信号。我们引入两种评估设置，自由形式标记和迭代标记，以评估不同的verbalized置信度估计方法。实验表明，我们的RL训练模型在三个长文问答数据集上实现了更好的校准，并在跨领域中表现出鲁棒的泛化能力。此外，我们的方法效率极高，比传统自一致性方法快20倍，同时实现了更好的校准。
英文摘要：
Hallucination remains a major challenge for the safe and trustworthy deployment of large language models (LLMs) in factual content generation. Prior work has explored confidence estimation as an effective approach to hallucination detection, but often relies on post-hoc self-consistency methods that require computationally expensive sampling. Verbalized confidence offers a more efficient alternative, but existing approaches are largely limited to short-form question answering (QA) tasks and do not generalize well to open-ended generation. In this paper, we propose LoVeC (Long-form Verbalized Confidence), a novel reinforcement learning based method that trains LLMs to append an on-the-fly numerical confidence score to each generated statement during long-form generation. The confidence score serves as a direct and interpretable signal of the factuality of generation. We introduce two evaluation settings, free-form tagging and iterative tagging, to assess different verbalized confidence estimation methods. Experiments on three long-form QA datasets show that our RL-trained models achieve better calibration and generalize robustly across domains. Also, our method is highly efficient, being 20 times faster than traditional self-consistency methods while achieving better calibration.
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。
