VISTA：基于顺序回合评估的验证
VISTA: Verification In Sequential Turn-based Assessment
AI总结：
VISTA通过声明级验证和顺序一致性追踪评估对话事实性，提升多轮对话中幻觉检测效果，改进现有基准测试的一致性。
摘要：
幻觉--在此定义为生成未被可用证据或对话上下文支持或矛盾的陈述--仍然是部署需要事实可靠性的对话AI系统的主要障碍。现有指标要么评估孤立响应，要么将不可验证的内容视为错误，限制了它们在多轮对话中的应用。我们引入VISTA（基于顺序回合评估的验证），一种通过声明级验证和顺序一致性追踪评估对话事实性的框架。VISTA将每个助手回合分解为原子事实性声明，通过可信来源和对话历史验证它们，并对不可验证的陈述（主观、矛盾、缺乏证据或回避）进行分类。在八个大语言模型和四个对话事实性基准（AIS、BEGIN、FAITHDIAL和FADE）上，VISTA在FACTSCORE和LLM-as-Judge基准上显著提高了幻觉检测效果。人工评估证实，VISTA的分解提高了标注者的一致性，并揭示了现有基准中的不一致。通过将事实性建模为对话的动态属性，VISTA提供了一种更透明、更符合人类的对话系统真实性度量标准。
英文摘要：
Hallucination--defined here as generating statements unsupported or contradicted by available evidence or conversational context--remains a major obstacle to deploying conversational AI systems in settings that demand factual reliability. Existing metrics either evaluate isolated responses or treat unverifiable content as errors, limiting their use for multi-turn dialogue. We introduce VISTA (Verification In Sequential Turn-based Assessment), a framework for evaluating conversational factuality through claim-level verification and sequential consistency tracking. VISTA decomposes each assistant turn into atomic factual claims, verifies them against trusted sources and dialogue history, and categorizes unverifiable statements (subjective, contradicted, lacking evidence, or abstaining). Across eight large language models and four dialogue factuality benchmarks (AIS, BEGIN, FAITHDIAL, and FADE), VISTA substantially improves hallucination detection over FACTSCORE and LLM-as-Judge baselines. Human evaluation confirms that VISTA's decomposition improves annotator agreement and reveals inconsistencies in existing benchmarks. By modeling factuality as a dynamic property of conversation, VISTA offers a more transparent, human-aligned measure of truthfulness in dialogue systems.
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。
