---
title: "LAQuer — paper by Hirsch et al. (2025) — summary and ideas"
description: "The authors define LAQuer, a task in which the user highlights any output span and the system returns… 29 references, cited by 5 papers here."
authors: ["Eran Hirsch", "Aviv Slobodkin", "David Wan", "Elias Stengel-Eskin", "Mohit Bansal", "Ido Dagan"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.746/"
doi: "10.18653/v1/2025.acl-long.746"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/hirsch-2025-laquer-localized-attribution-queries-content/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/hirsch-2025-laquer-localized-attribution-queries-content/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/10/) / LAQuer: Localized Attribution Queries in Content-grounded Generation

# LAQuer: Localized Attribution Queries in Content-grounded Generation

**Authors:** [Eran Hirsch](https://md.research.elamur.ai/free/en/authors/eran-hirsch/), [Aviv Slobodkin](https://md.research.elamur.ai/free/en/authors/aviv-slobodkin/), [David Wan](https://md.research.elamur.ai/free/en/authors/david-wan/), [Elias Stengel-Eskin](https://md.research.elamur.ai/free/en/authors/elias-stengel-eskin/), [Mohit Bansal](https://md.research.elamur.ai/free/en/authors/mohit-bansal/) and [Ido Dagan](https://md.research.elamur.ai/free/en/authors/ido-dagan/) · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.acl-long.746/) · [PDF](https://aclanthology.org/2025.acl-long.746.pdf) · [DOI 10.18653/v1/2025.acl-long.746](https://doi.org/10.18653/v1/2025.acl-long.746) · [OpenAlex](https://openalex.org/W4412945217)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/hirsch-2025-laquer-localized-attribution-queries-content/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Content-grounded generators, such as RAG systems, often produce claims that their sources do not support, so users have to check them. Most attribution methods cite evidence for whole sentences. That forces readers to look through long, mixed evidence even when they only care about one detail. Finer, sub-sentence methods exist, but their fixed spans may not match what a user actually wants to check.

The authors define LAQuer, a task in which the user highlights any output span and the system returns the minimal source spans supporting that fact. Their two-stage framework works as follows:
- The first stage generates text, with or without attribution metadata.
- The second stage decontextualizes the highlighted fact (for example, resolving pronouns) and then performs query-focused attribution. This is done either by prompting an LLM or by aligning phrases through the model's internal representations.

The framework is evaluated on Multi-document Summarization and Long-form Question Answering. User queries are simulated by splitting outputs into atomic facts, and support is scored with AutoAIS. Localized attribution greatly shortens the evidence users must read, but attributing decontextualized facts remains hard.

## Key points
- Three generation setups are benchmarked: plain Vanilla generation and two attributed-generation methods, including ATTR.FIRST. Existing sentence-level attributions, when available, are reused to narrow the search space.
- ATTR.FIRST performs best on contextualized facts. On decontextualized facts its scores drop to about 58 (MDS) and 53.6 (LFQA), because its original spans lack the context needed to resolve the decontextualized fact.
- An author-run human AIS check on 160 examples (80 per task) confirmed the automatic trends. A common failure was missing the document's broader theme.
- On the SPARK dataset, fact-level span attribution needs about 128 characters of reading, versus 278.5 for sentence-level spans, a 54% reduction.
- There is a cost trade-off: ATTR.FIRST generation uses roughly 90% longer prompts, but its subsequent LAQuer prompts are about ten times smaller than with Vanilla. Code is available at github.com/eranhirs/LAQuer.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Bar-Ilan University](https://md.research.elamur.ai/free/en/universities/bar-ilan-university/) — University, Ramat Gan, Israel · 146 works · 24,845 citations
- [University of North Carolina at Chapel Hill](https://md.research.elamur.ai/free/en/universities/university-of-north-carolina-at-chapel-hill/) — University, Chapel Hill, United States · 74 works · 23,278 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

## Cite

Cite as: Eran Hirsch, Aviv Slobodkin, David Wan, Elias Stengel-Eskin, Mohit Bansal and Ido Dagan. 2025. LAQuer: Localized Attribution Queries in Content-grounded Generation. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{hirsch2025laquer,
  title = {{LAQuer: Localized Attribution Queries in Content-grounded Generation}},
  author = {Eran Hirsch, Aviv Slobodkin, David Wan, Elias Stengel-Eskin, Mohit Bansal and Ido Dagan},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.746},
  url = {https://doi.org/10.18653/v1/2025.acl-long.746}
}
```

- [← previous IOLBENCH: Benchmarking LLMs on Linguistic Reasoning](https://md.research.elamur.ai/free/en/papers/goyal-2025-iolbench-benchmarking-llms-linguistic-reasoning/)
- [next → Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment](https://md.research.elamur.ai/free/en/papers/choi-2025-leveraging-allophony-self-supervised-speech/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/10/)

## References

29 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Satanjeev Banerjee and Alon Lavie. 2005. [METEOR: An automatic metric for MT evaluation with improved correlation with human judgments](https://md.research.elamur.ai/free/en/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/). In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pages 65–72, Ann Arbor, Michigan. Ass…
2. Bernd Bohnet, Vinh Q. Tran, Pat Verga, Roee Aharoni, Daniel Andor, Livio Baldini Soares, Massimiliano Ciaramita, Jacob Eisenstein, Kuzman Ganchev, Jonathan Herzig, Kai Hui, Tom Kwiatkowski, Ji Ma, Jianmo Ni, Lierni Sestorain Saralegui, Tal Schuster, William W. Cohen, Michael Collins, Dipanjan Das, D… — [Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models](https://md.research.elamur.ai/free/en/papers/bohnet-2022-attributed-question-answering-evaluation-modeling/)
3. Jan Buchmann, Xiao Liu, and Iryna Gurevych. 2024. Attribute or abstain: Large language models as long document assistants. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8113–8140, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jan+Buchmann%2C+Xiao+Liu%2C+and+Iryna+Gurevych%2E+2024%2E+Attribute+or+abstain%3A+Large+language+models+as+long+document+assistants%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natural+Languag)
4. Eunsol Choi, Jennimaria Palomaki, Matthew Lamm, Tom Kwiatkowski, Dipanjan Das, and Michael Collins. 2021. [Decontextualization: Making sentences stand-alone](https://md.research.elamur.ai/free/en/papers/choi-2021-decontextualization-making-sentences-stand-alone/). Transactions of the Association for Computational Linguistics, 9:447–461.
5. Benjamin Cohen-Wang, Harshay Shah, Kristian Georgiev, and Aleksander Madry. 2024. Contextcite: Attributing model generation to context. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Benjamin+Cohen%2DWang%2C+Harshay+Shah%2C+Kristian+Georgiev%2C+and+Aleksander+Madry%2E+2024%2E+Contextcite%3A+Attributing+model+generation+to+context%2E+In+The+Thirty%2Deighth+Annual+Conference+on+Neural+Information+Pro)
6. Qiang Ding, Lvzhou Luo, Yixuan Cao, and Ping Luo. 2024. Attention with dependency parsing augmentation for fine-grained attribution. Preprint, arXiv:2412.11404. [find](https://scholar.google.com/scholar?q=Qiang+Ding%2C+Lvzhou+Luo%2C+Yixuan+Cao%2C+and+Ping+Luo%2E+2024%2E+Attention+with+dependency+parsing+augmentation+for+fine%2Dgrained+attribution%2E+Preprint%2C+arXiv%3A2412%2E11404%2E)
7. Zi-Yi Dou and Graham Neubig. 2021. Word alignment by fine-tuning embeddings on parallel corpora. In Conference of the European Chapter of the Association for Computational Linguistics (EACL). [find](https://scholar.google.com/scholar?q=Zi%2DYi+Dou+and+Graham+Neubig%2E+2021%2E+Word+alignment+by+fine%2Dtuning+embeddings+on+parallel+corpora%2E+In+Conference+of+the+European+Chapter+of+the+Association+for+Computational+Linguistics+%28EACL%29%2E)
8. Ori Ernst, Ori Shapira, Aviv Slobodkin, Sharon Adar, Mohit Bansal, Jacob Goldberger, Ran Levy, and Ido Dagan. 2024. The power of summary-source alignments. In Findings of the Association for Computational Linguistics: ACL 2024, pages 6527–6548, Bangkok, Thailand. Association for Computational Lingui… [find](https://scholar.google.com/scholar?q=Ori+Ernst%2C+Ori+Shapira%2C+Aviv+Slobodkin%2C+Sharon+Adar%2C+Mohit+Bansal%2C+Jacob+Goldberger%2C+Ran+Levy%2C+and+Ido+Dagan%2E+2024%2E+The+power+of+summary%2Dsource+alignments%2E+In+Findings+of+the+Association+for+Computati)
9. Alexander Fabbri, Irene Li, Tianwei She, Suyi Li, and Dragomir Radev. 2019. [Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model](https://md.research.elamur.ai/free/en/papers/fabbri-2019-multi-news-large-scale-multi/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1074–1084, Florence, Italy.…
10. Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun Tejasvi Chaganty, Yicheng Fan, Vincent Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, and Kelvin Guu. 2023a. [RARR: Researching and revising what language models say, using language models](https://md.research.elamur.ai/free/en/papers/gao-2023-rarr-researching-revising-what-language/). In Proceedings of the 61st Annual Meeting of the Associat…
11. Tianyu Gao, Howard Yen, Jiatong Yu, and Danqi Chen. 2023b. [Enabling large language models to generate text with citations](https://md.research.elamur.ai/free/en/papers/gao-2023-enabling-large-language-models-generate/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6465–6488, Singapore. Association for Computational Linguistics.
12. Anisha Gunjal and Greg Durrett. 2024. Molecular facts: Desiderata for decontextualization in LLM fact verification. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3751–3768, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Anisha+Gunjal+and+Greg+Durrett%2E+2024%2E+Molecular+facts%3A+Desiderata+for+decontextualization+in+LLM+fact+verification%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2024%2C+pages+3751)
13. Or Honovich, Roee Aharoni, Jonathan Herzig, Hagai Taitelbaum, Doron Kukliansy, Vered Cohen, Thomas Scialom, Idan Szpektor, Avinatan Hassidim, and Yossi Matias. 2022. [TRUE: Re-evaluating factual consistency evaluation](https://md.research.elamur.ai/free/en/papers/honovich-2022-true-re-evaluating-factual-consistency/). In Proceedings of the 2022 Conference of the North American Chapter of the Associa…
14. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). In Advances in Neural Information Proc…
15. Chin-Yew Lin. 2004. [ROUGE: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
16. Nelson Liu, Tianyi Zhang, and Percy Liang. 2023. [Evaluating verifiability in generative search engines](https://md.research.elamur.ai/free/en/papers/liu-2023-evaluating-verifiability-generative-search-engines/). In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7001–7025, Singapore. Association for Computational Linguistics.
17. Jacob Menick, Maja Trebacz, Vladimir Mikulik, John Aslanides, Francis Song, Martin Chadwick, Mia Glaese, Susannah Young, Lucy Campbell-Gillingham, Geoffrey Irving, and Nat McAleese. 2022. [Teaching language models to support answers with verified quotes](https://md.research.elamur.ai/free/en/papers/menick-2022-teaching-language-models-support-answers/). ArXiv, abs/2203.11147.
18. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. [FActScore: Fine-grained atomic evaluation of factual precision in long form text generation](https://md.research.elamur.ai/free/en/papers/min-2023-factscore-fine-grained-atomic-evaluation/). In Proceedings of the 2023 Conference on Empirical Methods in Natural L…
19. Abhika Mishra, Akari Asai, Vidhisha Balachandran, Yizhong Wang, Graham Neubig, Yulia Tsvetkov, and Hannaneh Hajishirzi. 2024. [Fine-grained hallucination detection and editing for language models](https://md.research.elamur.ai/free/en/papers/mishra-2024-fine-grained-hallucination-detection-editing/). ArXiv, abs/2401.06855.
20. OpenAI. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv:2410.21276.
21. Preprint, Anirudh Phukan, Shwetha Somasundaram, Apoorv Saxena, Koustava Goswami, and Balaji Vasan Srinivasan. 2024. Peering into the mind of language models: An approach for attribution in contextual question answering. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11… [find](https://scholar.google.com/scholar?q=Preprint%2C+Anirudh+Phukan%2C+Shwetha+Somasundaram%2C+Apoorv+Saxena%2C+Koustava+Goswami%2C+and+Balaji+Vasan+Srinivasan%2E+2024%2E+Peering+into+the+mind+of+language+models%3A+An+approach+for+attribution+in+contextual+)
22. Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Sean Welleck, Yejin Choi, and Zaid Harchaoui. 2021. [Mauve: Measuring the gap between neural text and human text using divergence frontiers](https://md.research.elamur.ai/free/en/papers/pillutla-2021-mauve-measuring-gap-between-neural/). In NeurIPS.
23. Jirui Qi, Gabriele Sarti, Raquel Fernández, and Arianna Bisazza. 2024. Model internals-based answer attribution for trustworthy retrieval-augmented generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 6037–6053, Miami, Florida, USA. Association… [find](https://scholar.google.com/scholar?q=Jirui+Qi%2C+Gabriele+Sarti%2C+Raquel+Fern%C3%A1ndez%2C+and+Arianna+Bisazza%2E+2024%2E+Model+internals%2Dbased+answer+attribution+for+trustworthy+retrieval%2Daugmented+generation%2E+In+Proceedings+of+the+2024+Conference+on)
24. Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. [In-context retrieval-augmented language models](https://md.research.elamur.ai/free/en/papers/ram-2023-context-retrieval-augmented-language-models/). Transactions of the Association for Computational Linguistics, 11:1316–1331.
25. Hannah Rashkin, Vitaly Nikolaev, Matthew Lamm, Lora Aroyo, Michael Collins, Dipanjan Das, Slav Petrov, Gaurav Singh Tomar, Iulia Turc, and David Reitter. 2023. [Measuring attribution in natural language generation models](https://md.research.elamur.ai/free/en/papers/rashkin-2023-measuring-attribution-natural-language-generation/). Computational Linguistics, 49(4):777–840.
26. Tal Schuster, Adam Lelkes, Haitian Sun, Jai Gupta, Jonathan Berant, William Cohen, and Donald Metzler. 2024. SEMQA: Semi-extractive multi-source question answering. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Te… [find](https://scholar.google.com/scholar?q=Tal+Schuster%2C+Adam+Lelkes%2C+Haitian+Sun%2C+Jai+Gupta%2C+Jonathan+Berant%2C+William+Cohen%2C+and+Donald+Metzler%2E+2024%2E+SEMQA%3A+Semi%2Dextractive+multi%2Dsource+question+answering%2E+In+Proceedings+of+the+2024+Conferen)
27. Thibault Sellam, Dipanjan Das, and Ankur P Parikh. 2020. [Bleurt: Learning robust metrics for text generation](https://md.research.elamur.ai/free/en/papers/sellam-2020-bleurt-learning-robust-metrics-text/). In Proceedings of ACL.
28. Aviv Slobodkin, Eran Hirsch, Arie Cattan, Tal Schuster, and Ido Dagan. 2024. [Attribute first, then generate: Locally-attributable grounded text generation](https://md.research.elamur.ai/free/en/papers/slobodkin-2024-attribute-first-then-generate-locally/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3309–3344, Bangkok, Th…
29. Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam M. Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, Yaguang Li, Hongrae Lee, Huaixiu Steven Zheng, Amin Ghafouri, Marcelo Menegali, Yanping Input Length Output Length MDS [find](https://scholar.google.com/scholar?q=Romal+Thoppilan%2C+Daniel+De+Freitas%2C+Jamie+Hall%2C+Noam+M%2E+Shazeer%2C+Apoorv+Kulshreshtha%2C+Heng%2DTze+Cheng%2C+Alicia+Jin%2C+Taylor+Bos%2C+Leslie+Baker%2C+Yu+Du%2C+Yaguang+Li%2C+Hongrae+Lee%2C+Huaixiu+Steven+Zheng%2C+Amin+G)

*Updated 1 November 2026*