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.

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