How Interpretable are Reasoning Explanations from Prompting Large Language Models?
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
Prompt Engineering has garnered significant attention for enhancing the performance of large language models across a multitude of tasks.Techniques such as the Chain-of-Thought not only bolster task performance but also delineate a clear trajectory of reasoning steps, offering a tangible form of explanation for the audience.Prior works on interpretability assess the reasoning chains yielded by Chain-of-Thought solely along a singular axis, namely faithfulness.We present a comprehensive and multifaceted evaluation of interpretability, examining not only faithfulness but also robustness and utility across multiple commonsense reasoning benchmarks.Likewise, our investigation is not confined to a single prompting technique; it expansively covers a multitude of prevalent prompting techniques employed in large language models, thereby ensuring a wide-ranging and exhaustive evaluation.In addition, we introduce a simple interpretability alignment technique, termed Self-Entailment-Alignment Chain-of-thought, that yields more than 70% improvements across multiple dimensions of interpretability.Code is available at https://github.com/SenticNet/ CoT_interpretability
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
Large Language Models are Zero-Shot Reasoners
Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · arXiv · doi:10.48550/arxiv.2205.11916 · Cited by 2,013
Finetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101 · cited 1×
“Techniques such as instruct-tuning (Wei et al., 2021) applied across diverse tasks have empowered LLMs to execute inference on previously unseen tasks.”
BackgroundRationalizing Neural Predictions
Lei, T., Barzilay, R., & Jaakkola, T. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1011 · Cited by 777 · cited 1×
“Extractive rationalizing model (Lei et al., 2016), designed to be faithful, generally comprises two separate components: explainer and predictor.”
BackgroundHarnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond
Yang, J., Jin, H., Tang, R., Han, X., Feng, Q., Jiang, H., Yin, B., & Hu, X. (2023) · arXiv · doi:10.48550/arxiv.2304.13712 · Cited by 644
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness?
Jacovi, A., & Goldberg, Y. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.386 · Cited by 503
Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
Zhou, D., Schärli, N., Hou, L., Wei, J., Scales, N., Wang, X., Schuurmans, D., Cui, C., Bousquet, O., Le, Q., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.10625 · Cited by 380
Faithful Chain-of-Thought Reasoning
Lyu, Q., Havaldar, S., Stein, A., Zhang, L., Rao, D., Wong, E., Apidianaki, M., & Callison-Burch, C. (2023) · Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.ijcnlp-main.20 · Cited by 201
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Frantar, E., Ashkboos, S., Hoefler, T., & Alistarh, D. (2022) · arXiv · doi:10.48550/arxiv.2210.17323 · Cited by 197
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
Cited by
Kim, S. S. Y., Vaughan, J. W., Liao, Q. V., Lombrozo, T., & Russakovsky, O. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714020 · Cited by 58
Clinical insights: A comprehensive review of language models in medicine
Neveditsin, N., Lingras, P., & Mago, V. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000800 · Cited by 37
“A practical approach for handling such tasks is to refor-mulate them into well-defined tasks, such as classification or information extraction, along with incorporating the latest developments in reasoning and interpretability [248–250].”
Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective
Gabison, G. A., & Xian, R. P. (2025) · Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025) · doi:10.18653/v1/2025.realm-1.9 · Cited by 19
Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
Green, T., Gubri, M., Puerto, H., Yun, S., & Oh, S. J. (2025) · Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2025.emnlp-main.1347 · Cited by 10
LitFM: A Retrieval Augmented Structure-aware Foundation Model For Citation Graphs
Zhang, J., Maatouk, A., Chen, J., Bui, N., Xie, Q., Tassiulas, L., Xu, H., Shao, J., & Ying, R. (2025) · Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · doi:10.1145/3711896.3737028 · Cited by 6
“As a result, these methods struggle to retrieve the most relevant papers and lead to suboptimal performance.”
Metadata
- Authors
- Wei Jie, Y., Satapathy, R., Goh, R., & Cambria, E.
- Venue
- Findings of the Association for Computational Linguistics: NAACL 2024
- Published
- 2024
- Pages
- 2148-2164
- OpenAlex
- W4401043361
- Cited by
- 27
- References
- 16
- FWCI
- 8.21
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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: How Interpretable are Reasoning Explanations from Prompting Large Language Models? https://app.cochat.ai/papers/10.18653/v1/2024.findings-naacl.138
- The paper
- Wei Jie, Y., Satapathy, R., Goh, R., & Cambria, E. (2024). How Interpretable are Reasoning Explanations from Prompting Large Language Models? Findings of the Association for Computational Linguistics: NAACL 2024. https://doi.org/10.18653/v1/2024.findings-naacl.138
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.