2000 character limit reached
The Effect of Model Size on LLM Post-hoc Explainability via LIME
Published 8 May 2024 in cs.CL, cs.AI, and cs.LG | (2405.05348v1)
Abstract: LLMs are becoming bigger to boost performance. However, little is known about how explainability is affected by this trend. This work explores LIME explanations for DeBERTaV3 models of four different sizes on natural language inference (NLI) and zero-shot classification (ZSC) tasks. We evaluate the explanations based on their faithfulness to the models' internal decision processes and their plausibility, i.e. their agreement with human explanations. The key finding is that increased model size does not correlate with plausibility despite improved model performance, suggesting a misalignment between the LIME explanations and the models' internal processes as model size increases. Our results further suggest limitations regarding faithfulness metrics in NLI contexts.
- A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 632–642, Lisbon, Portugal, September 2015. Association for Computational Linguistics. doi: 10.18653/v1/D15-1075. URL https://aclanthology.org/D15-1075.
- Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
- e-snli: Natural language inference with natural language explanations. Advances in Neural Information Processing Systems, 31, 2018.
- A comparative study of faithfulness metrics for model interpretability methods. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5029–5038, Dublin, Ireland, May 2022. Association for Computational Linguistics. doi: 10.18653/v1/2022.acl-long.345. URL https://aclanthology.org/2022.acl-long.345.
- ERASER: A benchmark to evaluate rationalized NLP models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4443–4458, Online, July 2020. Association for Computational Linguistics. doi: 10.18653/v1/2020.acl-main.408. URL https://aclanthology.org/2020.acl-main.408.
- Attention is not Explanation. In 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), pp. 3543–3556, Minneapolis, Minnesota, June 2019. Association for Computational Linguistics. doi: 10.18653/v1/N19-1357. URL https://aclanthology.org/N19-1357.
- Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020.
- Towards faithful explanations for text classification with robustness improvement and explanation guided training. In Anaelia Ovalle, Kai-Wei Chang, Ninareh Mehrabi, Yada Pruksachatkun, Aram Galystan, Jwala Dhamala, Apurv Verma, Trista Cao, Anoop Kumar, and Rahul Gupta (eds.), Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023), pp. 1–14, Toronto, Canada, July 2023. Association for Computational Linguistics. doi: 10.18653/v1/2023.trustnlp-1.1. URL https://aclanthology.org/2023.trustnlp-1.1.
- A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, pp. 4768–4777, Red Hook, NY, USA, 2017. Curran Associates Inc. ISBN 9781510860964.
- Post-hoc interpretability for neural nlp: A survey. ACM Computing Surveys, 55(8):1–42, 2022.
- Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744, 2022.
- Explain yourself! leveraging language models for commonsense reasoning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4932–4942, Florence, Italy, July 2019. Association for Computational Linguistics. doi: 10.18653/v1/P19-1487. URL https://aclanthology.org/P19-1487.
- ” why should i trust you?” explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1135–1144, 2016.
- Anchors: High-precision model-agnostic explanations. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 2018.
- Do human rationales improve machine explanations? In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 56–62, Florence, Italy, August 2019. Association for Computational Linguistics. doi: 10.18653/v1/W19-4807. URL https://aclanthology.org/W19-4807.
- Gradient-based analysis of NLP models is manipulable. In Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 247–258, Online, November 2020. Association for Computational Linguistics. doi: 10.18653/v1/2020.findings-emnlp.24. URL https://aclanthology.org/2020.findings-emnlp.24.
- A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1112–1122, New Orleans, Louisiana, June 2018. Association for Computational Linguistics. doi: 10.18653/v1/N18-1101. URL https://aclanthology.org/N18-1101.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
