A Comparative Study of Faithfulness Metrics for Model Interpretability Methods (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to reveal the reasoning processes of machine learning models are difficult to interpret due to their complexity. |
| Approach: | They propose to use diagnosticity and complexity to assess faithfulness of machine learning models . they propose to apply posthoc interpretation methods to reveal reasoning behind models based on internal reasoning . |
| Outcome: | The proposed interpretation metrics show conflicting preferences when comparing interpretations . sufficiency and comprehensiveness metrics have higher diagnosticity and lower complexity . |
Similar Papers
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness? (2020.acl-main)
Copied to clipboard
| Challenge: | Current approaches to interpretability evaluation focus on faithfulness criteria . current approaches focus on readability, plausibility and faithfulness . |
| Approach: | They argue that current binary definition of faithfulness sets unrealistic standards . they argue that a more graded definition would be of greater practical utility . |
| Outcome: | The proposed approach is based on three assumptions and lacks a graded definition of faithfulness. |
A Causal Lens for Evaluating Faithfulness Metrics (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) offer natural language explanations as an alternative to feature attribution methods for model interpretability, but they may not reflect the model’s truereasoning faithfully. |
| Approach: | They propose a testbed framework for evaluating faithfulness metrics for natural language explanations using diagnosticity and model-editing methods. |
| Outcome: | The proposed framework evaluates faithfulness metrics for natural language explanations on four tasks including fact-checking, analogy, object counting, and multi-hop reasoning. |
Evaluating Readability and Faithfulness of Concept-based Explanations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluating concepts from different perspectives lack a unified formalization. |
| Approach: | They propose a formal definition of concepts generalizing to diverse concept-based explanations’ settings and apply it to other types of explanations or tasks. |
| Outcome: | Extensive experimental analysis was carried out to determine the evaluation measures for explanation evaluation measures. |
Analyzing and Evaluating Faithfulness in Dialogue Summarization (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on faithfulness of text summarization have not been conducted on abstractive summarizing. |
| Approach: | They propose a method to evaluate faithfulness of dialogue summarization models by multi-choice questions. |
| Outcome: | The proposed method can facilitate the development of dialogue summarization systems. |
Faithful Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work has focused on generating convincing rationales that appear to be subjectively faithful, but it remains unclear whether these explanations are epistemic faithful. |
| Approach: | They propose a method that enhances epistemic faithfulness by guiding explanation generation through attention-level interventions, informed by token-level heatmaps. |
| Outcome: | The proposed method significantly improves epistemic faithfulness across multiple models, benchmarks, and prompts. |
Are self-explanations from Large Language Models faithful? (2024.findings-acl)
Copied to clipboard
| Challenge: | Instruction-tuned Large Language Models excel at many tasks and will explain their reasoning, so-called self-explanations. |
| Approach: | They propose to employ self-consistency checks to measure faithfulness to LLMs to determine if they are model-dependent and if their reasoning is convincing and wrong. |
| Outcome: | The proposed measures show that self-explanations are explanation, model, and task-dependent and should not be trusted in general. |
Evaluating Saliency Methods for Neural Language Models (2021.naacl-main)
Copied to clipboard
| Challenge: | a general complaint of neural network models is that their internal decision mechanisms are hard to understand. |
| Approach: | They evaluate the quality of prediction interpretations from two perspectives: plausibility and faithfulness. |
| Outcome: | The evaluation of saliency methods on neural language models shows they can be trusted . the methods can be used to interpret the same prediction, but they disagree on interpretations . |
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for explaining "black-box" models such as Influence Functions are becoming more popular. |
| Approach: | They propose a semantic-based evaluation metric that can better align with humans’ judgment of explanations than the widely adopted diagnostic or re-training measures. |
| Outcome: | The proposed method can better align with humans’ judgment of explanations than diagnostic or re-training measures. |
Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Previous studies have investigated how different factors affect faithfulness of model explanations . |
| Approach: | They find that the larger the multilingual model, the less faithful FAs are compared to its counterpart monolingual models. |
| Outcome: | The results show that the larger the multilingual model, the less faithful the FAs are compared to its counterpart monolingual models. |
A Diagnostic Study of Explainability Techniques for Text Classification (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing explainability techniques that can be produced post-hoc with already trained models are lacking a definitive guide on how to choose one given a particular task and model architecture. |
| Approach: | They propose to use a list of diagnostic properties to evaluate existing explainability techniques to compare them with human annotations of salient input regions. |
| Outcome: | The proposed list compares a set of explainability techniques on downstream text classification tasks and neural network architectures. |