Challenge: Neural methods achieve high accuracy, but their representations lack direct interpretability.
Approach: They propose a method that supplements systems using interpretable features with a neural network to improve their performance while maintaining interpretability.
Outcome: The proposed method improves the performance of state-of-the-art models while maintaining interpretability.

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.
Who Wrote it and Why? Prompting Large-Language Models for Authorship Verification (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing AV techniques, including stylometric and deep learning, face limitations in terms of data requirements and lack of explainability.
Approach: They propose a technique that leverages Large-Language Models (LLMs) to provide step-by-step stylometric explanation prompts to verify authorship.
Outcome: The proposed technique outperforms state-of-the-art baselines, operates effectively with limited training data, and enhances interpretability through intuitive 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.
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods (2023.findings-acl)

Copied to clipboard

Challenge: A popular approach to unveiling the black box of neural NLP models is to leverage saliency methods, which assign scalar importance scores to each input component.
Approach: They propose to use saliency methods to evaluate whether an explanation is faithful and argue that Pearson-r is a better-suited alternative to rank correlation.
Outcome: The proposed methods exhibit weak rank correlations even when applied to the same model instance and advocated for alternative diagnostic 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.
CAVE: Controllable Authorship Verification Explanations (2025.naacl-long)

Copied to clipboard

Challenge: Authorship Verification (AV) is used for tasks such as plagiarism detection, forensic analysis, analysis of the spread of misinformation.
Approach: They propose to train an offline authorship verification model that is accessible and easy to use.
Outcome: The proposed model generates high quality explanations and competitive task accuracy on three difficult AV datasets.
Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods for predicting research replication are insufficient especially for long research papers.
Approach: They propose to build an interpretable neural model which can provide sentence-level explanations and apply weakly supervised approach to leverage large corpus of unlabeled datasets.
Outcome: The proposed model can provide sentence-level explanations and leverage large unlabeled datasets to boost interpretability and improve prediction performance.
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 .
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 .

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