# Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration

arXiv: https://arxiv.org/abs/2606.24970 · HTML: https://mlsanity.com/paper/2606.24970/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 62 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [Characterising Bias in Compressed Models](https://mlsanity.com/paper/2010.03058/) (2020)
- [Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods](https://mlsanity.com/paper/2402.02834/) (2024)
- [FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models](https://mlsanity.com/paper/2405.18218/) (2024)
- [The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning](https://mlsanity.com/paper/2310.04680/) (2023)
- [FASP: Fast and Accurate Structured Pruning of Large Language Models](https://mlsanity.com/paper/2501.09412/) (2025)

## Built on by (most cited first, 2 of 2)

- [Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning](https://mlsanity.com/paper/2609.00064/) (2026)
- [Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study](https://mlsanity.com/paper/2609.07395/) (2026)

## Abstract (arXiv)

Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of their accuracy. As attention layers are the most resource-intensive parts of LLMs, pruning them is a promising compression strategy. Prior work shows that up to 33% of attention layers can be pruned with minimal accuracy loss. Nevertheless, the impact of attention pruning on model interpretability, specifically faithfulness and confidence calibration, remains unstudied. To address this gap, we study how pruning attention layers affects explanation faithfulness and confidence calibration across five LLMs and eight datasets. While the pruned models often maintain high accuracy, we find that their faithfulness and calibration often degrade. Notably, faithfulness and calibration can fluctuate significantly, even when accuracy remains stable, highlighting a misalignment between model confidence, interpretability, and accuracy. Our findings suggest that layer pruning can affect LLMs' interpretability and reliability in ways not captured by accuracy and efficiency measures alone. We recommend including explainability and calibration metrics when evaluating pruned models.