Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions

• URL: http://arxiv.org/abs/2605.16877v1
• Date: Sat, 16 May 2026 08:39:05 GMT
• Title: Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions
• Abstract summary: textual explanations aim to make image classifiers more transparent by probing their internal representations.<n>FaithTrace measures how much the representation induced by the explanation changes the class logit.<n>We extend this influence score into quantitative evaluation metrics, helping fill the gap in faithfulness evaluation for textual explanations.
• Score: 12.961180148172199
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Zero-shot textual explanations aim to make image classifiers more transparent by probing their internal representations, without relying on task-specific supervision or LVLMs. However, existing methods often miss the features that truly drive the prediction, resulting in limited \textit{faithfulness} to the evidence underlying the model's decision. To address this, we propose FaithTrace. Motivated by the idea that faithful explanations should describe concepts that strongly influence the prediction, FaithTrace directly measures how much the representation induced by the explanation changes the class logit. We introduce an influence score, computed as the directional derivative of the class logit along the text-induced direction in the classifier's feature space, and use it as a proxy for faithfulness. Moreover, we extend this influence score into quantitative evaluation metrics, helping fill the gap in faithfulness evaluation for textual explanations. Experiments show that FaithTrace yields more faithful explanations than baselines, facilitating a more accurate understanding of the model. The code will be publicly released.

Related papers

• Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance [57.17102098930037]
  Large language models (LLMs) achieve strong performance and have revolutionized NLP.<n>Their lack of explainability keeps them treated as black boxes, limiting their use in domains that demand transparency and trust.<n>We introduce a training-free method that enhances faithfulness by guiding explanation generation through attention-level interventions.
  arXiv  Detail & Related papers  (2026-04-15T18:32:32Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models [29.67884478799914]
  Large Language Models (LLMs) are capable of generating persuasive Natural Language Explanations (NLEs) to justify their answers. Recent studies have proposed various methods to measure the faithfulness of NLEs, typically by inserting perturbations at the explanation or feature level. We argue that these approaches are neither comprehensive nor correctly designed according to the established definition of faithfulness.
  arXiv  Detail & Related papers  (2024-10-18T03:45:42Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• On the Faithfulness of Vision Transformer Explanations [23.963269554498716]
  Post-hoc explanations assign salience scores to input pixels, providing human-understandable heatmaps. We introduce Salience-guided Faithfulness Coefficient (SaCo), a novel evaluation metric leveraging essential information of salience distribution. Our SaCo demonstrates that the use of gradient and multi-layer aggregation can markedly enhance the faithfulness of attention-based explanation.
  arXiv  Detail & Related papers  (2024-04-01T18:41:30Z)
• FaithLM: Towards Faithful Explanations for Large Language Models [60.45183469474916]
  We introduce FaithLM, a model-agnostic framework that evaluates and improves the faithfulness of large language models.<n>We show that FaithLM consistently increases faithfulness and produces explanations more aligned with human rationales than strong self-explanation baselines.
  arXiv  Detail & Related papers  (2024-02-07T09:09:14Z)
• Regressor-Segmenter Mutual Prompt Learning for Crowd Counting [70.49246560246736]
  We propose mutual prompt learning (mPrompt) to solve bias and inaccuracy caused by annotation variance. Experiments show that mPrompt significantly reduces the Mean Average Error (MAE)
  arXiv  Detail & Related papers  (2023-12-04T07:53:59Z)
• Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors [3.4253416336476246]
  We focus on the analysis of counterfactual, contrastive explanations. We propose a new back translation-inspired evaluation methodology. We show that by iteratively feeding the counterfactual to the explainer we can obtain valuable insights into the behaviour of both the predictor and the explainer models.
  arXiv  Detail & Related papers  (2023-05-26T16:04:28Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)

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.