HalluCana:基于金丝雀前瞻机制修复大语言模型幻觉
HalluCana: Fixing LLM Hallucination with A Canary Lookahead
AI总结:
本研究提出名为HalluCana的金丝雀前瞻机制,利用LLM隐藏空间的内部事实性表示,在生成过程中甚至生成前及时检测并干预事实性幻觉,在传记生成任务上实现质量最高提升2.5倍、计算消耗降低6倍以上的效果。
摘要:
本文提出HalluCana——一种金丝雀前瞻机制,用于检测并纠正大语言模型(LLM)在长文本生成中的事实性幻觉。该方法在生成过程中甚至生成前,一旦出现幻觉迹象便立即检测并干预。为实现及时检测,我们利用LLM隐藏空间中的内部事实性表示,探究了多种LLM事实性自我评估的代理指标,并讨论了其与模型预训练带来的上下文熟悉度的关联。在传记生成任务上,该方法将生成质量最高提升2.5倍,同时计算消耗降低6倍以上。
英文摘要:
In this paper, we present HalluCana, a canary lookahead to detect and correct factuality hallucinations of Large Language Models (LLMs) in long-form generation. HalluCana detects and intervenes as soon as traces of hallucination emerge, during and even before generation. To support timely detection, we exploit the internal factuality representation in the LLM hidden space, where we investigate various proxies to the LLMs' factuality self-assessment, and discuss its relation to the models' context familiarity from their pre-training. On biography generation, our method improves generation quality by up to 2.5x, while consuming over 6 times less compute.
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。