Lynx:一个开源的幻觉评估模型
Lynx: An Open Source Hallucination Evaluation Model
AI总结:
为解决LLM幻觉问题,提出SOTA幻觉检测模型LYNX与包含1.5万样本的HaluBench基准,实验证明其性能优于GPT-4o等模型,并已开源。
摘要:
检索增强生成(RAG)技术旨在缓解大型语言模型(LLMs)中的幻觉问题。然而,LLMs仍可能生成不受支持或与检索上下文相矛盾的信息。我们提出了LYNX,这是一个SOTA幻觉检测LLM,能够在具有挑战性的真实世界幻觉场景中进行高级推理。为评估LYNX,我们推出了HaluBench,这是一个全面的幻觉评估基准,包含1.5万个来自各种真实世界领域的样本。实验结果表明,在HaluBench上,LYNX优于GPT-4o、Claude-3-Sonnet以及闭源和开源的LLM-as-a-judge模型。我们公开发布了LYNX、HaluBench及评估代码。
英文摘要:
Retrieval Augmented Generation (RAG) techniques aim to mitigate hallucinations in Large Language Models (LLMs). However, LLMs can still produce information that is unsupported or contradictory to the retrieved contexts. We introduce LYNX, a SOTA hallucination detection LLM that is capable of advanced reasoning on challenging real-world hallucination scenarios. To evaluate LYNX, we present HaluBench, a comprehensive hallucination evaluation benchmark, consisting of 15k samples sourced from various real-world domains. Our experiment results show that LYNX outperforms GPT-4o, Claude-3-Sonnet, and closed and open-source LLM-as-a-judge models on HaluBench. We release LYNX, HaluBench and our evaluation code for public access.
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。