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.

Similar Papers

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 .
Interpretability and Analysis in Neural NLP (2020.acl-tutorials)

Copied to clipboard

Challenge: a tutorial aims to introduce the nascent field of interpretability and analysis of neural networks in NLP .
Approach: This tutorial will introduce the nascent field of interpretability and analysis of neural networks in NLP.
Outcome: This tutorial will introduce the nascent field of interpretability and analysis of neural networks in NLP.
On the Sensitivity and Stability of Model Interpretations in NLP (2022.acl-long)

Copied to clipboard

Challenge: Recent years have witnessed the emergence of post-hoc interpretations that aim to uncover how NLP models make predictions.
Approach: They propose two new criteria that provide complementary notions of faithfulness to removal-based criteria.
Outcome: The proposed methods overcome limitations of gradient-based methods on removal-based criteria and overcome limitations in the proposed methods.
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.
Neuron-level Interpretation of Deep NLP Models: A Survey (2022.tacl-1)

Copied to clipboard

Challenge: Existing work on deep neural networks has focused on representation analysis, but recent work focused on analyzing neurons within these models.
Approach: They propose to analyze neural networks to uncover linguistic concepts captured by the network . they propose to use a granular approach to analyze neurons within these models .
Outcome: The proposed method combines methods to discover and understand neurons in a network with evaluation methods.
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 .
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.
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.
SHAP-Based Explanation Methods: A Review for NLP Interpretability (2022.coling-1)

Copied to clipboard

Challenge: Existing models with opacity problems have been proposed to address this problem.
Approach: They propose a unified local-interpretability framework with a rigorous theoretical foundation on the game-theoretic concept of Shapley values.
Outcome: The proposed framework is based on the Shapley-value-based model explanations.
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations