Challenge: XAI features usually provide a single importance score for each token, but feature attribution methods provide two complementary and theoretically-grounded scores for each utterance.
Approach: They propose a feature attribution method that generates explicit perturbations of the input text, allowing the importance scores themselves to be explainable.
Outcome: The proposed method explain the predictions of hate speech detection models on a set of curated examples from a test suite.

Similar Papers

Incorporating Priors with Feature Attribution on Text Classification (P19-1)

Copied to clipboard

Challenge: Feature attribution methods are used to help users interpret complex models.
Approach: They propose a feature attribution method that integrates feature attributed features into the objective function to allow machine learning practitioners to incorporate priors in model building.
Outcome: The proposed method reduces undesired model biases without a tradeoff on the original task and improves classifier performance in scarce data setting.
Explanation Regularisation through the Lens of Attributions (2025.coling-main)

Copied to clipboard

Challenge: Explanation regularisation (ER) is a method to guide text classifiers to form their predictions relying on tokens that humans consider plausible.
Approach: They introduce an auxiliary explanation loss to measure how well an input attribution technique's output agrees with human-annotated rationales.
Outcome: The proposed model improves classification performance in out-of-domain (OOD) settings by relying on tokens humans consider plausible.
Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings (2024.lrec-main)

Copied to clipboard

Challenge: Currently, prompt-based models are gaining popularity due to their easier adaptability in low-resource settings.
Approach: They analyze attribution scores extracted from prompt-based models w.r.t. plausibility and faithfulness and compare them with attribution score extracted from fine-tuned models and large language models.
Outcome: The proposed model outperforms attention and Integrated Gradients in plausibility and faithfulness, while fine-tuning models are harder to explain in low-resource settings.
Exploring the Usability of Persuasion Techniques for Downstream Misinformation-related Classification Tasks (2024.lrec-main)

Copied to clipboard

Challenge: systematically explore the predictive power of features derived from Persuasion Techniques detected in texts for different tasks of interest for media analysis.
Approach: They propose a set of meaningful features aimed at capturing persuasiveness of a text . they also assess the discriminatory power of these features in different text classification tasks .
Outcome: The proposed features can be applied to detecting mis/disinformation, fake news, propaganda, partisan news and conspiracy theories.
Features or Spurious Artifacts? Data-centric Baselines for Fair and Robust Hate Speech Detection (2022.naacl-main)

Copied to clipboard

Challenge: lexical biases in hate speech detection are limited when applied to real-world data, exhibiting limited out-of-distribution robustness and perpetuating harmful social biase.
Approach: They propose to disentangle spurious and authentic artifacts and analyze their impact on out-of-distribution fairness and robustness.
Outcome: The proposed models show that spurious artifacts require different treatments to attain robustness and fairness in hate speech detection.
Interpretable Text Embeddings and Text Similarity Explanation: A Survey (2025.emnlp-main)

Copied to clipboard

Challenge: Text embeddings are a fundamental component in many NLP tasks, but their interpretation and explanation remain challenging.
Approach: They propose a framework for interpretable text embeddings and text similarity explanation . they characterize the main ideas, approaches, and trade-offs and discuss lessons learned .
Outcome: The proposed methods are compared with existing models and compare them with existing ones.
Towards Explainable Hate Speech Detection (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in deep learning have significantly enhanced the efficiency and accuracy of natural language processing (NLP) tasks.
Approach: They propose a model that uses valence, arousal, and dominance (VAD) scores to detect hate speech and a weighted sum of valent, valance, and valency (VA) scores for classification.
Outcome: The proposed model can compete with state-of-the-art models in detecting hate speech and non-hate speech words based on their individual and summed VAD-values.
“Will You Find These Shortcuts?” A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification (2022.emnlp-main)

Copied to clipboard

Challenge: Existing work on faithfulness evaluation is not conclusive and does not provide a clear answer as to how different methods are to be compared.
Approach: They propose a protocol for faithfulness evaluation that makes use of partially synthetic data to obtain ground truth for feature importance ranking.
Outcome: The proposed method is based on partially synthetic data and is compared with lexical shortcuts on a range of datasets and LSTM models.
Incorporating Attribution Importance for Improving Faithfulness Metrics (2023.acl-long)

Copied to clipboard

Challenge: Feature attribution methods (FAs) are popular for providing insights into the model reasoning process of making predictions.
Approach: They propose a simple yet effective criterion that randomly masks tokens proportionately to their FA importance.
Outcome: The proposed method is more faithful than hard sufficiency and comprehensiveness metrics.
ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection (2022.emnlp-main)

Copied to clipboard

Challenge: Hate speech detection is complex and requires commonsense reasoning and social nuance . prior work has shown that even humans cannot achieve a high agreement on whether a post constitutes HS .
Approach: They frame a few-shot learning task to decompose a hate speech detection task into its "constituent" parts. they show that infusing commonsense knowledge from reasoning datasets improves the performance even further.
Outcome: The proposed method outperforms baseline methods in the 16-shot case.

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