Measuring Attribution in Natural Language Generation Models
Open accessThe DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Abstract
Large neural models have brought a new challenge to natural language generation (NLG): It has become imperative to ensure the safety and reliability of the output of models that generate freely. To this end, we present an evaluation framework, Attributable to Identified Sources (AIS), stipulating that NLG output pertaining to the external world is to be verified against an independent, provided source. We define AIS and a two-stage annotation pipeline for allowing annotators to evaluate model output according to annotation guidelines. We successfully validate this approach on generation datasets spanning three tasks (two conversational QA datasets, a summarization dataset, and a table-to-text dataset). We provide full annotation guidelines in the appendices and publicly release the annotated data at https://github.com/google-research-datasets/AIS.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures









Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Rashkin et al. propose23 and formalize a framework called Attributable to Identifiable Sources, which defines the AIS score of a given language model’s response”
From An automated framework for assessing how well LLMs cite relevant medical references (2025) · cites this paper as [23]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Citation-grade attribution requires locatable evidence: a reader must be able to retrieve and check the cited source (Rashkin et al., 2023;Bohnet et al., 2022).”
From The Attribution-Compression Frontier in Retrieval-Augmented Generation (2026) · cites this paper as Rashkin et al., 2023
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The AIS framework evaluates whether statements are supported by identified sources (Rashkin et al., 2023).”
From The Attribution-Compression Frontier in Retrieval-Augmented Generation (2026) · cites this paper as Rashkin et al., 2023
In the citing paper
“Compliance with stringent legal standards within applicable jurisdictions, such as the General Data Protection Regulation (GDPR) and California Consumer Privacy Act (CCPA), is essential, necessitating purpose limitation and data minimization [230], [231], [232].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [230]
In the citing paper
“Rashkin et al. (2023) define the”
From Enabling Large Language Models to Generate Text with Citations (2023) · cites this paper as Rashkin et al. (2023)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Grice, H. P. (1975) · Speech Acts · doi:10.1163/9789004368811_003 · Cited by 23,221
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 2×
“…that paper, we also compared with three models that are seq2seq-style conversation models: the original answer generation system from Dinan et al. (2019), the Dodecadialogue multitask system from Shuster et al. (2020) and a T5-base model (Raffel et al., 2020) finetuned on Wizard of Wikipedia data.”
BackgroundGet To The Point: Summarization with Pointer-Generator Networks
See, A., Liu, P. J., & Manning, C. D. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1099 · Cited by 3,775 · cited 1×
“Lastly, we used Pointer-generator Networks from See et al. (2017) — a hybrid approach that is uses an abstractive seq2seq model but with an explicit copy mechanism that can extract information from the source document.”
MethodAbstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, R., Zhou, B., dos Santos, C., Gulcehre, C., & Xiang, B. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1028 · Cited by 2,361 · cited 7×
“We observed that the reference summaries in CNN/DM may sometimes refer to external pieces of information that may have accompanied the article (a picture, a headline, etc.) or sometimes make assumptions about what the intended audience of the article might already know that can affect either the interpretability or AI…”
BackgroundMethodInfluentialNatural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069
Self-citationBig Bird: Transformers for Longer Sequences
Zaheer, M., Guruganesh, G., Dubey, A., Ainslie, J., Alberti, C., Ontanon, S., Pham, P., Ravula, A., Wang, Q., Yang, L., et al. (2020) · arXiv · doi:10.48550/arxiv.2007.14062 · Cited by 1,349 · cited 1×
“We also used an abstractive summarization system, BigBird (Zaheer et al., 2020).”
MethodFEVER: a Large-scale Dataset for Fact Extraction and VERification
Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1074 · Cited by 1,343 · cited 1×
“A related field of study has dealt with the topic of fact or claim verification (Thorne et al., 2018; Thorne and Vlachos, 2018; Thorne et al., 2021, inter alia).”
BackgroundOn Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.173 · Cited by 1,185
On Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · arXiv · doi:10.48550/arxiv.2005.00661 · Cited by 1,185 · cited 4×
“Maynez et al. (2020) presented an extensive characterization of hallucinations, discussed behavior of models that generate content that are present in larger corpora beyond a given source and conducted a significant human study.”
BackgroundResultInfluentialWhy the child’s theory of mind really is a theory
GOPNIK, A., & WELLMAN, H. M. (1992) · Mind & Language · doi:10.1111/j.1468-0017.1992.tb00202.x · Cited by 1,158
QuAC: Question Answering in Context
Choi, E., He, H., Iyyer, M., Yatskar, M., Yih, W.-T., Choi, Y., Liang, P., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1241 · Cited by 714 · cited 2×
“2019), QUAC (Choi et al. 2018), and CAST-19 (Dalton et al.”
MethodModel-Agnostic Interpretability of Machine Learning
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · arXiv · doi:10.48550/arxiv.1606.05386 · Cited by 699 · cited 1×
“Ribeiro et al. (2016)).”
Towards a Human-like Open-Domain Chatbot
Adiwardana, D., Luong, M.-T., So, D. R., Hall, J., Fiedel, N., Thoppilan, R., Yang, Z., Kulshreshtha, A., Nemade, G., Lu, Y., et al. (2020) · arXiv · doi:10.48550/arxiv.2001.09977 · Cited by 614
Wizard of Wikipedia: Knowledge-Powered Conversational agents
Dinan, E., Roller, S., Shuster, K., Fan, A., Auli, M., & Weston, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.01241 · Cited by 572 · cited 7×
“We used the seen portion of the test set from Wizard of Wikipedia (Dinan et al. 2019).”
BackgroundMethodResultInfluentialChallenges in Data-to-Document Generation
Wiseman, S., Shieber, S., & Rush, A. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1239 · Cited by 524 · cited 1×
“Wiseman et al. (2017) presented challenges in data-to-text generation where neural models generate hallucinated content not supported by source data; they proposed an automatic information extraction-based metric to evaluate generated text for that particular scenario and conducted a small human…”
BackgroundMental Representations: The Interface between Language and Reality
Everett, D. L., & Kempson, R. M. (1991) · Language · doi:10.2307/415145 · Cited by 419
Extractive Summarization as Text Matching
Zhong, M., Liu, P., Chen, Y., Wang, D., Qiu, X., & Huang, X. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.552 · Cited by 413
(2020) · doi:10.18653/v1/2020.acl-main.450 · Cited by 356
Asking and Answering Questions to Evaluate the Factual Consistency of Summaries
Wang, A., Cho, K., & Lewis, M. (2020) · arXiv · doi:10.48550/arxiv.2004.04228 · Cited by 356
Howcroft, D. M., Belz, A., Clinciu, M., Gkatzia, D., Hasan, S. A., Mahamood, S., Mille, S., van Miltenburg, E., Santhanam, S., & Rieser, V. (2020) · International Conference on Natural Language Generation · doi:10.18653/v1/2020.inlg-1.23 · Cited by 319
Durmus, E., He, H., & Diab, M. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.454 · Cited by 306
Combining Fact Extraction and Verification with Neural Semantic Matching Networks
Nie, Y., Chen, H., & Bansal, M. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016859 · Cited by 265
ToTTo: A Controlled Table-To-Text Generation Dataset
Parikh, A., Wang, X., Gehrmann, S., Faruqui, M., Dhingra, B., Yang, D., & Das, D. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.89 · Cited by 252
Self-citationToTTo: A Controlled Table-To-Text Generation Dataset
Parikh, A. P., Wang, X., Gehrmann, S., Faruqui, M., Dhingra, B., Yang, D., & Das, D. (2020) · arXiv · doi:10.48550/arxiv.2004.14373 · Cited by 252 · cited 3×
“More recently, Parikh et al. (2020) presented a larger human evaluation study in the context of a data-to-text generation dataset entitled ToTTo, and measured hallucinations in terms of faithfulness with respect to a source data table.”
BackgroundMethodSelf-citationDialogue Natural Language Inference
Welleck, S., Weston, J., Szlam, A., & Cho, K. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1363 · Cited by 249 · cited 2×
“These have been measured via dialogue-specific natural language inference methods, often via human studies and data creation (Welleck et al. 2019; Mehri and Eskenazi 2020; Gupta et al. 2021; Honovich et al. 2021; Dziri et al. 2021; Santhanam et al. 2021).”
MethodInherent Disagreements in Human Textual Inferences
Pavlick, E., & Kwiatkowski, T. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00293 · Cited by 214
Automated Fact Checking: Task formulations, methods and future directions
Thorne, J. P., & Vlachos, A. (2018) · arXiv (Cornell University) · doi:10.17863/cam.78745 · Cited by 212
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics
Pagnoni, A., Balachandran, V., & Tsvetkov, Y. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.383 · Cited by 197
Harvey Friedman's Research on the Foundations of Mathematics
(1985) · Studies in Logic and the Foundations of Mathematics · doi:10.1016/s0049-237x(09)x7008-4 · Cited by 185 · cited 1×
“…extends to a much larger set of system utterances, in particular giving a treatment of interpretability2, and contex- 2We acknowledge that the term “interpretability” has come to signify “model interpretability” in the NLP and ML community (as established in Harrington et al. (1985), tual effects.”
BackgroundThe GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
Gehrmann, S., Adewumi, T., Aggarwal, K., Ammanamanchi, P. S., Aremu, A., Bosselut, A., Chandu, K. R., Clinciu, M.-A., Das, D., Dhole, K., et al. (2021) · Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021) · doi:10.18653/v1/2021.gem-1.10 · Cited by 159
Self-citationUSR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation
Mehri, S., & Eskenazi, M. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.64 · Cited by 149
Open-Domain Question Answering Goes Conversational via Question Rewriting
Anantha, R., Vakulenko, S., Tu, Z., Longpre, S., Pulman, S., & Chappidi, S. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.44 · Cited by 130
Honovich, O., Choshen, L., Aharoni, R., Neeman, E., Szpektor, I., & Abend, O. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.619 · Cited by 113 · cited 1×
“…extends to a much larger set of system utterances, in particular giving a treatment of interpretability2, and contex- 2We acknowledge that the term “interpretability” has come to signify “model interpretability” in the NLP and ML community (as established in Harrington et al. (1985), tual effects.”
BackgroundImproving Factual Consistency of Abstractive Summarization via Question Answering
Nan, F., Nogueira dos Santos, C., Zhu, H., Ng, P., McKeown, K., Nallapati, R., Zhang, D., Wang, Z., Arnold, A. O., & Xiang, B. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.536 · Cited by 78
Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features
Rashkin, H., Reitter, D., Tomar, G. S., & Das, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.58 · Cited by 74 · cited 3×
“The general trend of results is similar to what was found in the human evaluations of faithfulness and subjectivity in Rashkin et al. (2021).”
MethodResultSelf-citationThe Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents
Shuster, K., JU, D., Roller, S., Dinan, E., Boureau, Y.-L., & Weston, J. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.222 · Cited by 71
CAsT-19: A Dataset for Conversational Information Seeking
Dalton, J., Xiong, C., Kumar, V., & Callan, J. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401206 · Cited by 61 · cited 1×
“Set-up We use the QReCC dataset (Anantha et al., 2021), a collection of multi-turn conversational QA interactions that extends conversations coming from NaturalQuestions (Kwiatkowski et al., 2019), QUAC (Choi et al., 2018), and CAST-19 (Dalton et al., 2020).”
MethodDecontextualization: Making Sentences Stand-Alone
Choi, E., Palomaki, J., Lamm, M., Kwiatkowski, T., Das, D., & Collins, M. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00377 · Cited by 54 · cited 3×
“A key idea in our model of meaning in context is the notion of explicatures (Carston 1988; Wilson and Sperber 2004; Choi et al. 2021).”
BackgroundResultInfluentialSelf-citationThe GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
Gehrmann, S., Adewumi, T., Aggarwal, K., Ammanamanchi, P. S., Anuoluwapo, A., Bosselut, A., Chandu, K. R., Clinciu, M., Das, D., Dhole, K. D., et al. (2021) · arXiv · doi:10.48550/arxiv.2102.01672 · Cited by 49
Self-citationDialFact: A Benchmark for Fact-Checking in Dialogue
Gupta, P., Wu, C.-S., Liu, W., & Xiong, C. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.263 · Cited by 48
Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark
Dziri, N., Rashkin, H., Linzen, T., & Reitter, D. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00506 · Cited by 47 · cited 2×
“These have been measured via dialogue-specific natural language inference methods, often via human studies and data creation (Welleck et al. 2019; Mehri and Eskenazi 2020; Gupta et al. 2021; Honovich et al. 2021; Dziri et al. 2021; Santhanam et al. 2021).”
MethodSelf-citationEvaluating Attribution in Dialogue Systems: The BEGIN Benchmark
Dziri, N., Rashkin, H., Linzen, T., & Reitter, D. (2021) · arXiv · doi:10.48550/arxiv.2105.00071 · Cited by 47
Self-citationLadhak, F., Durmus, E., He, H., Cardie, C., & McKeown, K. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.100 · Cited by 46
Belz, A., Mille, S., & Howcroft, D. M. (2020) · Proceedings of the 13th International Conference on Natural Language Generation · doi:10.18653/v1/2020.inlg-1.24 · Cited by 45 · cited 1×
“Human evaluation studies are varied from paper to paper and detailed, reproducible annotation instructions are unavailable (Belz et al., 2020).”
BackgroundSanthanam, S., Hedayatnia, B., Gella, S., Padmakumar, A., Kim, S., Liu, Y., & Hakkani-Tur, D. (2021) · arXiv · doi:10.48550/arxiv.2110.05456 · Cited by 21
Evidence-based Verification for Real World Information Needs.Preprint
Thorne, J., Glockner, M., Vallejo, G., Vlachos, A., & Gurevych, I. (2021) · arXiv (Cornell University) · Cited by 18
Research works printed but not linked: 2
- Carston, 1988, Implicature, explicature, and truth-theoretic semantics, 155
- Wilson, 2004, Relevance theory, 607
Cited by
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
“…generated by large language models are coherent or factually correct, as underscored by the recent work evaluating the factuality of language model generations and explanations (Maynez et al., 2020; Rashkin et al., 2021; Ye and Durrett, 2022; Marasovi ´ c et al., 2022; Wiegreffe et al., 2022).”
HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
Li, J., Cheng, X., Zhao, W. X., Nie, J.-Y., & Wen, J.-R. (2023) · arXiv · doi:10.48550/arxiv.2305.11747 · Cited by 340
“…the utterances generated by dialogue systems into three categories, i.e., fully attributable, not fully attributable, and generic; and the Attributable to Identified Sources (AIS) benchmark (Rashkin et al., 2021) assesses whether the source documents support the output of text generation models.”
BackgroundChain-of-Verification Reduces Hallucination in Large Language Models
Dhuliawala, S., Komeili, M., Xu, J., Raileanu, R., Li, X., Celikyilmaz, A., & Weston, J. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.212 · Cited by 282
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.05232 · Cited by 2,516
Enabling Large Language Models to Generate Text with Citations
Gao, T., Yen, H., Yu, J., & Chen, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.398 · Cited by 216
Metadata
- Authors
- Rashkin, H., Nikolaev, V., Lamm, M., Aroyo, L., Collins, M., Das, D., Petrov, S., Tomar, G. S., Turc, I., & Reitter, D.
- Affiliations
- Google DeepMind (United Kingdom) (GB)
- Google (United States) (US)
- Storia AI. iulia@iuliaturc.com
- ORCID
- Venue
- Computational Linguistics
- Publisher
- MIT Press
- Published
- 2023
- Volume
- 49
- Issue
- 4
- Pages
- 777-840
- ISSN
- 0891-2017 (ISSN-L)
- 1530-9312
- OpenAlex
- W4381432831
- Cited by
- 71
- References
- 46
- Citations by year
- 2026: 37 · 2025: 20 · 2024: 8 · 2023: 6
- FWCI
- 6.69
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Computational Linguistics (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- attribution, natural language generation, evaluation framework, annotation guidelines, annotation pipeline, conversational question answering, summarization, table-to-text generation, model safety
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.