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

• URL: http://arxiv.org/abs/2606.24970v1
• Date: Tue, 23 Jun 2026 11:07:59 GMT
• Title: Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration
• Abstract summary: Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network.<n>We study how pruning attention layers affects explanation faithfulness and confidence calibration across five LLMs and eight datasets.<n>Our findings suggest that layer pruning can affect LLMs' interpretability and reliability in ways not captured by accuracy and efficiency measures alone.
• Score: 17.14392068503777
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction [51.56484100374058]
  Existing calibration methods for Large Language Models (LLMs) often overlook a critical dimension of trustworthiness: a model's behavioral robustness.<n>We introduce textscCaliDist, a novel post-hoc calibration approach that directly measures and penalizes a model's susceptibility to distraction.<n>textscCaliDist consistently achieves lower Expected Error (ECE) and Brier Score compared with strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T07:27:53Z)
• Discovery of Hidden Miscalibration Regimes [52.452902154360565]
  Models may be systematically overconfident on some kinds of inputs and underconfident on others.<n>We define the corresponding miscalibration field and propose a diagnostic framework for estimating it.<n>Our approach learns a calibration-aware representation of the input space and estimates signed local miscalibration by kernel smoothing in the learned geometry.
  arXiv  Detail & Related papers  (2026-05-13T13:07:50Z)
• Does Visual Token Pruning Improve Calibration? An Empirical Study on Confidence in MLLMs [0.0]
  We study how visual token pruning affects model calibration, that is, whether predicted confidence matches actual correctness.<n>Our results show that pruning does not simply trade reliability for efficiency.
  arXiv  Detail & Related papers  (2026-04-13T20:24:03Z)
• On Calibration of Large Language Models: From Response To Capability [66.59139960234326]
  Large language models (LLMs) are widely deployed as general-purpose problem solvers.<n>We introduce capability calibration, which targets the model's expected accuracy on a query.<n>Our results demonstrate that capability-calibrated confidence improves pass@$k$ prediction and inference budget allocation.
  arXiv  Detail & Related papers  (2026-02-14T01:07:45Z)
• Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning [10.123352394689134]
  Well-calibrated confidence enables downstream systems to decide when to trust a model and when to defer to fallback mechanisms.<n>We show that while RLVR improves task performance, it produces extremely overconfident models.<n>We propose a calibration-aware reinforcement learning formulation that directly adjusts decision-token probabilities.
  arXiv  Detail & Related papers  (2026-01-19T18:31:31Z)
• ConfTuner: Training Large Language Models to Express Their Confidence Verbally [58.63318088243125]
  Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as science, law, and healthcare.<n>LLMs are often observed to generate incorrect answers with high confidence, a phenomenon known as "overconfidence"
  arXiv  Detail & Related papers  (2025-08-26T09:25:32Z)
• Calibrated Language Models and How to Find Them with Label Smoothing [12.584298923765688]
  Large language models (LLMs) can behave as more powerful interactive agents through improved instruction-following ability.<n>Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability.<n> understanding how this impacts confidence calibration for reliable model output has not been researched in full.
  arXiv  Detail & Related papers  (2025-08-01T02:12:20Z)
• MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs [66.14178164421794]
  We introduce MetaFaith, a novel prompt-based calibration approach inspired by human metacognition.<n>We show that MetaFaith robustly improves faithful calibration across diverse models and task domains, enabling up to 61% improvement in faithfulness.
  arXiv  Detail & Related papers  (2025-05-30T17:54:08Z)
• Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models [0.6091702876917281]
  Large Language Models (LLMs) show remarkable proficiency in natural language tasks.<n>Overconfidence-misalignment between predicted confidence and true correctness poses significant risks in critical decision-making applications.<n>We present a comprehensive analysis on calibration in LLMs across nine LLMs and three factual Question-Answering datasets.
  arXiv  Detail & Related papers  (2025-02-16T07:46:09Z)
• Few-Shot Recalibration of Language Models [23.829795148520834]
  We train a recalibration model that takes in a few unlabeled examples from any given slice and predicts a curve that remaps confidence scores to be more accurate for that slice. Our trained model can recalibrate for arbitrary new slices, without using any labeled data from that slice. Experiments show that our few-shot recalibrator consistently outperforms existing calibration methods.
  arXiv  Detail & Related papers  (2024-03-27T06:25:40Z)
• Calibrating Large Language Models with Sample Consistency [76.23956851098598]
  We explore the potential of deriving confidence from the distribution of multiple randomly sampled model generations, via three measures of consistency. Results show that consistency-based calibration methods outperform existing post-hoc approaches. We offer practical guidance on choosing suitable consistency metrics for calibration, tailored to the characteristics of various LMs.
  arXiv  Detail & Related papers  (2024-02-21T16:15:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.