基于子序列关联过滤与广度感知选择的大语言模型查询扩展中幻觉术语的追踪与抑制
Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion
AI总结：
针对大语言模型查询扩展的幻觉问题，提出无需训练的SAFE-QE方法，在保持排序质量的同时大幅减少无支持的幻觉术语，在TREC、BEIR数据集上验证了其有效性。
摘要：
大语言模型（LLMs）目前是查询扩展术语的标准来源，但会产生幻觉：它们会注入不存在的实体和偏离主题的术语，增加排序噪声并损害强大的检索器。现有补救措施（如语料库 grounding、相互验证和偏好对齐）将幻觉术语视为需通过一致性启发式方法过滤的无差别干扰项，既未解释特定术语出现的机制，也未确定保留术语数量的原则性标准。我们提出子序列关联过滤广度感知查询扩展（SAFE-QE），这是一种无需训练、与检索器无关的方法，基于幻觉的子序列关联解释。我们通过候选扩展术语在随机查询语境下的语料库条件跨语境可复现性对其打分：在随机查询语境下重复出现但在伪相关集中缺乏支持的术语被标记为主导幻觉关联的产物并被降权。我们将语言生成描述为一致性（无幻觉）与广度（覆盖度）之间的权衡，将术语选择建模为对伪相关集的约束覆盖最大化，保留一组近似广度、一致且在重采样中稳定的术语。我们还引入幻觉扩展术语率，这是一种查询侧忠实度指标，用于统计无相关文档支持的注入扩展术语数量。我们在基准 TREC 和 BEIR 数据集上评估我们的方法。我们的 SAFE-QE 在 nDCG@10 上与生成式和语料库引导的扩展方法无统计差异，同时注入的无支持术语更少：每个查询 4.3 个，而 Query2doc 为 27.8 个、HyDE 为 57.5 个；在强大的学习型稀疏检索器上，所有扩展方法均出现性能下降，因此忠实度的提升不会带来可测量的排序质量损失。
英文摘要：
Large language models (LLMs) are now a standard source of query expansion terms but they hallucinate. They inject non existent entities and off-topic terms that add ranking noise and can hurt strong retrievers. Existing remedies such as corpus grounding, mutual verification and preference alignment treat hallucinated terms as an undifferentiated nuisance to be filtered by agreement heuristics, without a mechanistic account of why a given term appears or a principled criterion for how many terms to keep. We propose Subsequence-Association Filtered, breadth-aware query expansion (SAFE-QE), a training-free, retriever agnostic method that draws on the subsequence-association account of hallucination. We score each candidate expansion term by its corpus conditioned cross-context reproducibility, terms that reappear under randomised query contexts yet lack support in the pseudo-relevant set are flagged as products of dominant hallucinatory associations and down-weighted. Drawing on the characterisation of language generation as a trade-off between consistency (no hallucination) and breadth (coverage), we cast term selection as constrained coverage maximisation over the pseudo-relevant set, keeping a set that is approximately broad but consistent and stable across resampling. We also introduce the Hallucinated Expansion Term Rate, a query side faithfulness metric that counts injected expansion terms no relevant document supports. We evaluate our approach on benchmarked TREC and BEIR collections. Our SAFE-QE is statistically indistinguishable from generative and corpus-steered expansion on nDCG@10 while injecting fewer unsupported terms 4.3 per query against 27.8 for Query2doc and 57.5 for HyDE and on a strong learned sparse retriever, where every expansion method regresses. Faithfulness is therefore available at no measurable cost in ranking quality.
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。
