arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.21731cs.CLcs.AIcs.IR
收藏

已检索但未读取:探究搜索增强型大语言模型为何无法使用可用证据

Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence

Imperial College London(帝国理工学院)

Owen Walters, Lihu Chen, Francesca Toni

AI总结:

该研究针对搜索增强型大语言模型存在的检索证据未被有效利用的问题,通过构建时间事实、评估不同模型配置,发现模型常基于搜索片段直接作答,即便证据影响内部预测仍可能偏向过时信息,相关发现可推动该领域研究。

摘要:

网络搜索使大语言模型(LLMs)能够获取最新信息,但即便存在相关证据,它们有时仍会生成过时答案,其原因尚不明确。为研究该问题,我们构建了在模型训练截止日期后数值发生变化的时间事实,在部署的网络搜索环境下评估1个专有模型,在受控检索环境下评估6个开放权重模型配置。我们发现,模型常直接基于搜索片段作答而不打开源页面,这与过时答案和不实引用率升高相关。我们的受控实验及分层分析显示,证据的可用性与其有效利用之间存在差距:即便检索到的证据会影响内部预测,模型最终答案仍可能偏向过时信息。我们希望这些发现能推动搜索增强型大语言模型可靠利用检索证据的研究进展。

英文摘要:

Web search allows LLMs to access up-to-date information, but it remains unclear why they sometimes produce outdated answers even when relevant evidence is available. To study this problem, we construct temporal facts whose values changed after the models' training cutoffs. We evaluate one proprietary model under deployed web search and six open-weight model configurations under controlled retrieval. We find that models often answer from search snippets without opening the source pages, which is associated with higher rates of outdated answers and unfaithful citations. Our controlled experiments and layer-wise analysis reveal a gap between the availability of evidence and its effective use. Even when retrieved evidence influences internal predictions, models may still favour outdated information in their final answers. We hope these findings will help advance research on the reliable use of retrieved evidence in search-augmented LLMs.

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。

↑