--- title: "Localizing Factual Inconsistencies in Attributable Text Generation" description: "The authors propose QASemConsistency. 1 reference, cited by 7 papers here. Among them: 0." authors: ["Arie Cattan", "Paul Roit", "Shiyue Zhang", "David Wan", "Roee Aharoni", "Idan Szpektor", "Mohit Bansal", "Ido Dagan"] year: 2026 venue: "Transactions of the Association for Computational Linguistics" source: "https://aclanthology.org/2026.tacl-1.6/" doi: "10.1162/tacl.a.598" 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/cattan-2026-localizing-factual-inconsistencies-attributable-text/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/cattan-2026-localizing-factual-inconsistencies-attributable-text/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/2/) / Localizing Factual Inconsistencies in Attributable Text Generation # Localizing Factual Inconsistencies in Attributable Text Generation **Authors:** [Arie Cattan](https://md.research.elamur.ai/free/en/authors/arie-cattan/), [Paul Roit](https://md.research.elamur.ai/free/en/authors/paul-roit/), [Shiyue Zhang](https://md.research.elamur.ai/free/en/authors/shiyue-zhang/), [David Wan](https://md.research.elamur.ai/free/en/authors/david-wan/), [Roee Aharoni](https://md.research.elamur.ai/free/en/authors/roee-aharoni/), [Idan Szpektor](https://md.research.elamur.ai/free/en/authors/idan-szpektor/), [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:** 2026 · **Venue:** [Transactions of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/tacl/) ([Transactions of the Association for Computational Linguistics (TACL) 2026](https://md.research.elamur.ai/free/en/venues/tacl/2026/)) · **Publisher:** [The MIT Press](https://md.research.elamur.ai/free/en/publishers/the-mit-press/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.tacl-1.6/) · [PDF](https://aclanthology.org/2026.tacl-1.6.pdf) · [DOI 10.1162/tacl.a.598](https://doi.org/10.1162/tacl.a.598) · [OpenAlex](https://openalex.org/W7119679804) **Citations:** 0 citations (OpenAlex, 2026-10-14) · [7](https://md.research.elamur.ai/free/en/papers/cattan-2026-localizing-factual-inconsistencies-attributable-text/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary LLM outputs that should be grounded in a reference document, such as summaries, open-book answers or cited responses, still contain hallucinations. Existing detectors usually flag whole sentences, spans, or "atomic" claims that bundle several facts together, so they cannot show exactly which piece of information is wrong. The authors propose QASemConsistency. Drawing on Neo-Davidsonian semantics, it splits a generated text into minimal propositions. Each proposition is one predicate–argument relation, written as a simple question–answer pair in the QA-SRL (verbs) and QANom (nominalizations) formats. Each pair is then judged as supported or unsupported by the reference. Because the pairs are plain natural language, crowd workers can label them. The authors built a benchmark of over 3K instances covering several attributable generation tasks, with substantial inter-annotator agreement. They also show that the resulting consistency scores track human judgments. Automatic detection was tested with supervised NLI models and prompted open and commercial LLMs. These handle such fine-grained hypotheses reasonably well but leave much room for improvement. The work offers a precise, human-usable unit for evaluating and correcting hallucinations. ## Key points - Text is decomposed via QA-SRL and QANom, so each QA pair encodes a single semantic relation. It is compared against token-level (CLIFF), QGQA (Q²), claim-level (FActScore), and structured approaches (DAE, FactGraph). - In 27% of predicates, some of their QA pairs were supported and others were not. Coarser claim-level units would miss this distinction. - The crowdsourced benchmark has more than 3K instances. For contrast, span highlighting in CLIFF reached only 0.35 Fleiss Kappa. - Detectors were built from NLI models trained on standard entailment data and from open-source and commercial LLMs. Code, data and models are released on the first author's GitHub (github.com/ariecattan). - Limitations: only verbal and nominal predicates are covered, so errors in adjectives or discourse relations are not isolated at the finest level. The authors suggest QADiscourse or QA-Adj as possible extensions. Published in TACL vol. 14 (2026). *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 · 141 works · 23,225 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 · 67 works · 16,474 citations - [Google (Israel)](https://md.research.elamur.ai/free/en/companies/google-israel/) — Company, Haifa, Israel · 2 works · 37 citations 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 577 works 🧭 Topics (1): [✍️ Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/) · 202 works ## Cite Cite as: Arie Cattan, Paul Roit, Shiyue Zhang, David Wan, Roee Aharoni, Idan Szpektor, Mohit Bansal and Ido Dagan. 2026. Localizing Factual Inconsistencies in Attributable Text Generation. Transactions of the Association for Computational Linguistics. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @article{cattan2026localizing, title = {{Localizing Factual Inconsistencies in Attributable Text Generation}}, author = {Arie Cattan, Paul Roit, Shiyue Zhang, David Wan, Roee Aharoni, Idan Szpektor, Mohit Bansal and Ido Dagan}, journal = {Transactions of the Association for Computational Linguistics}, year = {2026}, doi = {10.1162/tacl.a.598}, url = {https://doi.org/10.1162/tacl.a.598} } ``` - [← previous Localized Cultural Knowledge is Conserved and Controllable in Large Language Models](https://md.research.elamur.ai/free/en/papers/veselovsky-2026-localized-cultural-knowledge-is-conserved/) - [next → MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning](https://md.research.elamur.ai/free/en/papers/fu-2026-maspo-unifying-gradient-utilization-probability/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/2/) ## References 1 references, 1 of them with a card of ours. ↗ leads to the work. 1. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. [The Berkeley FrameNet project](https://md.research.elamur.ai/free/en/papers/baker-1998-berkeley-framenet/). In 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 1, pages 86–90, Montreal, Quebec, Canada. Association for Comput… *Updated 31 October 2026*