Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales

• URL: http://arxiv.org/abs/2606.01148v1
• Date: Sun, 31 May 2026 10:35:35 GMT
• Title: Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales
• Abstract summary: This paper compares two families of explanations for question answering models: verbalized feature attributions and self-generated rationales.<n>We analyze how explanation source, verbalization strategy, and feature granularity affect the simulatability of explanations.
• Score: 1.8772057593980798
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Natural-language explanations are often treated as a unified interface for understanding model behavior, but different explanation sources may support simulation in different ways. This paper compares two families of explanations for question answering models: verbalized feature attributions and self-generated rationales. We evaluate them under a shared counterfactual simulation setting, using an LLM judge as predictor and measuring whether it can better predict a model's answers to follow-up questions when given its explanation. Across multiple instruction-tuned models, we analyze how explanation source, verbalization strategy, and feature granularity affect the simulatability of explanations. Our results show that explanation format and granularity affect simulatability: attribution-based explanations and self-generated rationales differ in how much they improve counterfactual prediction, with effects that vary across models and formats.

Related papers

• Evaluating the Ability of Explanations to Disambiguate Models in a Rashomon Set [10.788168368884804]
  We propose three principles of explanation evaluation and a new method "AXE" to evaluate the quality of feature-importance explanations.<n>We show how evaluation metrics that rely on comparing model explanations against ideal ground truth explanations obscure behavioral differences within a Rashomon set.
  arXiv  Detail & Related papers  (2026-01-13T16:31:11Z)
• Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations [1.8772057593980798]
  Large Language Models (LLMs) can produce verbalized self-explanations.<n>We evaluate how well humans and LLM judges can predict a model's answers to counterfactual follow-up questions.
  arXiv  Detail & Related papers  (2026-01-07T10:13:26Z)
• Explanation sensitivity to the randomness of large language models: the case of journalistic text classification [6.240875403446504]
  We study the effect of random elements in the training of large language models on the explainability of their predictions. Using a fine-tuned CamemBERT model and an explanation method based on relevance propagation, we find that training with different random seeds produces models with similar accuracy but variable explanations.
  arXiv  Detail & Related papers  (2024-10-07T14:39:45Z)
• Causal Generative Explainers using Counterfactual Inference: A Case Study on the Morpho-MNIST Dataset [5.458813674116228]
  We present a generative counterfactual inference approach to study the influence of visual features as well as causal factors. We employ visual explanation methods from OmnixAI open source toolkit to compare them with our proposed methods. This finding suggests that our methods are well-suited for generating highly interpretable counterfactual explanations on causal datasets.
  arXiv  Detail & Related papers  (2024-01-21T04:07:48Z)
• Explainability for Large Language Models: A Survey [59.67574757137078]
  Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. This paper introduces a taxonomy of explainability techniques and provides a structured overview of methods for explaining Transformer-based language models.
  arXiv  Detail & Related papers  (2023-09-02T22:14:26Z)
• MaNtLE: Model-agnostic Natural Language Explainer [9.43206883360088]
  We introduce MaNtLE, a model-agnostic natural language explainer that analyzes multiple classifier predictions. MaNtLE uses multi-task training on thousands of synthetic classification tasks to generate faithful explanations. Simulated user studies indicate that, on average, MaNtLE-generated explanations are at least 11% more faithful compared to LIME and Anchors explanations.
  arXiv  Detail & Related papers  (2023-05-22T12:58:06Z)
• Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models [77.34726150561087]
  We define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. This paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications.
  arXiv  Detail & Related papers  (2022-03-30T05:59:50Z)
• Interpreting Language Models with Contrastive Explanations [99.7035899290924]
  Language models must consider various features to predict a token, such as its part of speech, number, tense, or semantics. Existing explanation methods conflate evidence for all these features into a single explanation, which is less interpretable for human understanding. We show that contrastive explanations are quantifiably better than non-contrastive explanations in verifying major grammatical phenomena.
  arXiv  Detail & Related papers  (2022-02-21T18:32:24Z)
• Evaluating Explanations: How much do explanations from the teacher aid students? [103.05037537415811]
  We formalize the value of explanations using a student-teacher paradigm that measures the extent to which explanations improve student models in learning. Unlike many prior proposals to evaluate explanations, our approach cannot be easily gamed, enabling principled, scalable, and automatic evaluation of attributions.
  arXiv  Detail & Related papers  (2020-12-01T23:40:21Z)
• Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? [86.60613602337246]
  We introduce a leakage-adjusted simulatability (LAS) metric for evaluating NL explanations. LAS measures how well explanations help an observer predict a model's output, while controlling for how explanations can directly leak the output. We frame explanation generation as a multi-agent game and optimize explanations for simulatability while penalizing label leakage.
  arXiv  Detail & Related papers  (2020-10-08T16:59:07Z)
• Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? [97.77183117452235]
  We carry out human subject tests to isolate the effect of algorithmic explanations on model interpretability. Clear evidence of method effectiveness is found in very few cases. Our results provide the first reliable and comprehensive estimates of how explanations influence simulatability.
  arXiv  Detail & Related papers  (2020-05-04T20:35:17Z)

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.