mlsanityData to 14 Oct 2026

The Effect of Model Size on LLM Post-hoc Explainability via LIME

arXiv 2405.05348 ↗First posted 8 May 2024cs.CL cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Large language models (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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 16 of its 17 references that are in the map. First posted on arXiv 8 May 2024.

Builds on

16 of 17 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2020Scaling Laws for Neural Language Modelscited by 6,586
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  6. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  7. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  8. 2019Attention is not Explanationcited by 929
  9. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  10. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  11. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  12. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 156
4 more
  1. 2020Gradient-based Analysis of NLP Models is Manipulablecited by 41
  2. 2022A Comparative Study of Faithfulness Metrics for Model Interpretability Methodscited by 39
  3. 2019Do Human Rationales Improve Machine Explanations?cited by 33
  4. 2023Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Trainingcited by 4

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024Linearly-Interpretable Concept Embedding Models for Text Analysiscited by 3
  2. 2025Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Frameworkcited by 1
  3. 2025Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persiancited by 0
  4. 2025Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attributioncited by 0