The DOI matches its Crossref record; 84 of the 88 references it cites were found in a registry or an index, and 1 are not checked yet.
Measuring Association Between Labels and Free-Text Rationales
Open accessAbstract
In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance.While prior work focuses on extractive rationales (a subset of the input words), we investigate their lessstudied counterpart: free-text natural language rationales.We demonstrate that pipelines, models for faithful rationalization on informationextraction style tasks, do not work as well on "reasoning" tasks requiring free-text rationales.We turn to models that jointly predict and rationalize, a class of widely used high-performance models for free-text rationalization.We investigate the extent to which the labels and rationales predicted by these models are associated, a necessary property of faithful explanation.Via two tests, robustness equivalence and feature importance agreement, we find that stateof-the-art T5-based joint models exhibit desirable properties for explaining commonsense question-answering and natural language inference, indicating their potential for producing faithful free-text rationales. 1
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“While largerscale evaluations are desirable, prior work (Rudin, 2019; Wiegreffe et al., 2021) has shown that even small samples, when selected for conceptual diversity and difficulty, yield robust insights into model behavior.”
From GIER: Gap-Driven Self-Refinement for Large Language Models (2025) · cites this paper as Wiegreffe et al., 2021
Experimental — accuracy not yet measured
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
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
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
A large annotated corpus for learning natural language inference
Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1075 · Cited by 3,377
Towards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
Research works printed but not linked: 2
- Miruna-Adriana Clinciu, Arash Eshghi, and Helen Hastie. 2021. A study of automatic metrics for the evaluation of natural language explanations. In Pro- ceedings of the 16th Conference of the European Chapter of the Association for Computational Lin- guistics: Main Volume, pages 2376-2387, Online. Association for Computational Linguistics.
- Omar Zaidan and Jason Eisner. 2008. Modeling an- notators: A generative approach to learning from annotator rationales. In Proceedings of the 2008 Conference on Empirical Methods in Natural Lan- guage Processing, pages 31-40, Honolulu, Hawaii. Association for Computational Linguistics.
Cited by
Sorted by citations
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
“That line of work typically focuses on natural language inference (Camburu et al., 2018; Yordanov et al., 2021; Bostrom et al., 2021), and produces explanations either simultaneously to or after the final prediction (Narang et al., 2020; Majumder et al., 2021; Wiegreffe et al., 2021, 2022).”
Hsieh, C.-Y., Li, C.-L., Yeh, C.-K., Nakhost, H., Fujii, Y., Ratner, A., Krishna, R., Lee, C.-Y., & Pfister, T. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.507 · Cited by 316
Towards Faithful Model Explanation in NLP: A Survey
Lyu, Q., Apidianaki, M., & Callison-Burch, C. (2024) · Computational Linguistics · doi:10.1162/coli_a_00511 · Cited by 196
Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models
Louis, A., DIJCK, G. V., & Spanakis, G. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i20.30232 · Cited by 132
Teach Me to Explain: A Review of Datasets for Explainable Natural Language ProcessingPreprint
Wiegreffe, S., & Marasović, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.12060 · Cited by 128
Self-citation
Metadata
- Authors
- Wiegreffe, S., Marasović, A., & Smith, N. A.
- Affiliations
- Georgia Institute of Technology (US)
- Venue
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Published
- 2021
- Pages
- 10266-10284
- OpenAlex
- W3093530468
- Cited by
- 119
- References
- 88
- Citations by year
- 2026: 9 · 2025: 17 · 2024: 22 · 2023: 29 · 2022: 24 · 2021: 18
- FWCI
- 10.37
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Allen Institute for Artificial Intelligence
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- interpretability, commonsense question answering, natural language inference, T5
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
