# LAQuer: Localized Attribution Queries in Content-grounded Generation Source: [LAQuer: Localized Attribution Queries in Content-grounded Generation]() Collection index: [llms.txt]() Data updated: 2026-01-02T10:13:29.533Z Authors: Eran Hirsch, Aviv Slobodkin, David Wan, Elias Stengel-Eskin, Mohit Bansal, Ido Dagan Published: 2025-06-01T21:46:23.000Z ## Abstract Grounded text generation models often produce content that deviates from their source material, requiring user verification to ensure accuracy. Existing attribution methods associate entire sentences with source documents, which can be overwhelming for users seeking to fact-check specific claims. In contrast, existing sub-sentence attribution methods may be more precise but fail to align with users' interests. In light of these limitations, we introduce Localized Attribution Queries (LAQuer), a new task that localizes selected spans of generated output to their corresponding source spans, allowing fine-grained and user-directed attribution. We compare two approaches for the LAQuer task, including prompting large language models (LLMs) and leveraging LLM internal representations. We then explore a modeling framework that extends existing attributed text generation methods to LAQuer. We evaluate this framework across two grounded text generation tasks: Multi-document Summarization (MDS) and Long-form Question Answering (LFQA). Our findings show that LAQuer methods significantly reduce the length of the attributed text. Our contributions include: (1) proposing the LAQuer task to enhance attribution usability, (2) suggesting a modeling framework and benchmarking multiple baselines, and (3) proposing a new evaluation setting to promote future research on localized attribution in content-grounded generation. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Long-form Question Answering on LFQA](): Long-form Question Answering; LFQA; AIS (Decomposition): 59.5. - [Multi-Document Summarization Citation Evaluation on MDS](): Multi-Document Summarization citation evaluation; MDS; AIS DECON: 39. - [Multi-document Summarization on MDS](): Multi-document summarization; MDS; Length: 41.6. - [Long-Form Question Answering on LFQA (test)](): Long-form Question Answering; LFQA (test); R-L: not recorded. - [Multi-Document Summarization on MDS SPARK (test)](): Multi-document summarization; MDS SPARK (test); ROUGE-L: not recorded. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()