Aligning Faithful Interpretations with their Social Attribution
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
We find that the requirement of model interpretations to be faithful is vague and incomplete. With interpretation by textual highlights as a case study, we present several failure cases. Borrowing concepts from social science, we identify that the problem is a misalignment between the causal chain of decisions (causal attribution) and the attribution of human behavior to the interpretation (social attribution). We reformulate faithfulness as an accurate attribution of causality to the model, and introduce the concept of aligned faithfulness: faithful causal chains that are aligned with their expected social behavior. The two steps of causal attribution and social attribution together complete the process of explaining behavior. With this formalization, we characterize various failures of misaligned faithful highlight interpretations, and propose an alternative causal chain to remedy the issues. Finally, we implement highlight explanations of the proposed causal format using contrastive explanations.
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
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.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“It is a property inspired by human-given explanations, which are post-hoc stories generated to plausibly justify our actions (Rudin, 2019).”
BackgroundRecursive 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
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
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
An Experimental Study of Apparent Behavior
Heider, F., & Simmel, M. (1944) · The American Journal of Psychology · doi:10.2307/1416950 · Cited by 3,340
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
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., & Sayres, R. (2017) · arXiv · doi:10.48550/arxiv.1711.11279 · Cited by 1,240
Attention is not not Explanation
Wiegreffe, S., & Pinter, Y. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1002 · Cited by 966 · cited 1×
“When formalizing the desired properties of a quality interpretation of a model or a decision, the NLP community has settled on the key property of faithfulness (Lipton, 2018; Herman, 2017; Wiegreffe and Pinter, 2019; Jacovi and Goldberg, 2020), or how ‘‘accurately’’ the interpretation represents the true reasoning pro…”
Background
Cited by
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
Jacovi, A., Marasović, A., Miller, T., & Goldberg, Y. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445923 · Cited by 545
“fails us, but this is not true for reliance because we did not attribute intent to the trustee [68]. Despite the fact that AI models are tools, people anthropomorphize them and assign intent to them [30, 52]. This makes us believe that reliance is not suitable for AI models, and for this reason we aim to define Human-…”
BackgroundSelf-citationExplainability of Deep Vision-Based Autonomous Driving Systems: Review and Challenges
Zablocki, É., Ben-Younes, H., Pérez, P., & Cord, M. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01657-x · Cited by 227
Explainability of deep vision-based autonomous driving systems: Review and challenges
Zablocki, É., Ben-Younes, H., Pérez, P., & Cord, M. (2021) · arXiv · doi:10.48550/arxiv.2101.05307 · Cited by 227
Measuring Association Between Labels and Free-Text Rationales
Wiegreffe, S., Marasović, A., & Smith, N. A. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.804 · Cited by 119
Measuring Association Between Labels and Free-Text Rationales
Wiegreffe, S., Marasović, A., & Smith, N. A. (2020) · arXiv · doi:10.48550/arxiv.2010.12762 · Cited by 106
Metadata
- Authors
- Jacovi, A., & Goldberg, Y.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2021
- Volume
- 9
- Pages
- 294-310
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W3032150215
- Cited by
- 73
- References
- 27
- FWCI
- 5.29
- Type
- journal article
- Language
- en
- Open access
- diamond
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Aligning Faithful Interpretations with their Social Attribution. https://app.cochat.ai/papers/10.1162/tacl_a_00367
- The paper
- Jacovi, A., & Goldberg, Y. (2021). Aligning Faithful Interpretations with their Social Attribution. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00367
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.