Papers with explainability methods
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA (2022.aacl-demo)
Copied to clipboard
Rachneet Sachdeva, Haritz Puerto, Tim Baumgärtner, Sewin Tariverdian, Hao Zhang, Kexin Wang, Hossain Shaikh Saadi, Leonardo F. R. Ribeiro, Iryna Gurevych
| Challenge: | Question Answering (QA) systems rely on deep neural networks, which are difficult to interpret by humans. |
| Approach: | They propose an interpretable model that provides an explanation infrastructure for comparing models based on saliency maps and graph-based explanations. |
| Outcome: | The proposed methods can be used to compare models based on saliency maps and graph-based explanations. |
Layerwise Relevance Visualization in Convolutional Text Graph Classifiers (D19-53)
Copied to clipboard
| Challenge: | Existing explainability methods do not focus on intermediate states in hidden layers of Deep Neural Networks (DNNs). |
| Approach: | They propose a method that visits visible and hidden layers of a deep neural network and projects them onto the interpretable domain. |
| Outcome: | The proposed method yields meaningful layerwise explanations for a GCN sentence classifier. |
The Hidden Attention of Mamba Models (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that Mamba models can be used for multiple domains, including NLP, long-range sequence processing, and computer vision. |
| Approach: | They add a third view and show that Mamba models can be viewed as attention-driven models. |
| Outcome: | The proposed model can be viewed as attention-driven and empirically compare it to the attention-based models of transformers. |
Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales (2024.findings-naacl)
Copied to clipboard
| Challenge: | Saliency post-hoc explainability methods are important tools for understanding complex NLP models, but they may not align with human intuition, making the explanations not plausible. |
| Approach: | They propose a method for incorporating rationales into text classification models by augmenting the standard cross-entropy loss with a novel loss function inspired by contrastive learning. |
| Outcome: | The proposed approach enhances the plausibility of post-hoc explanations while preserving their faithfulness. |
From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs (2025.findings-naacl)
Copied to clipboard
Navya Jain, Zekun Wu, Cristian Enrique Munoz Villalobos, Airlie Hilliard, Xin Guan, Adriano Koshiyama, Emre Kazim, Philip Colin Treleaven
| Challenge: | Methods like prompt-based In-Context Knowledge Editing and gradient-based Model Editor Networks (MEND) show irregularity and variability; IKE depends on the prompt, leading to variability and sensitivity; MEND yields inconsistent and gibberish outputs. |
| Approach: | They employ Opinion QA Based Parameter-Efficient Fine-Tuning (PEFT) to manipulate the Big Five personality traits: Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. |
| Outcome: | The proposed methods show that they are more accurate than prompt-based IKE and gradient-based MEND outputs. |
An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records (2024.emnlp-main)
Copied to clipboard
| Challenge: | State-of-the-art explainability methods rely on human annotations, which are costly. |
| Approach: | They propose an approach to produce plausible and faithful explanations without annotations . they use adversarial robustness training to improve plausibility and AttInGrad . |
| Outcome: | The proposed method produces plausible explanations without human annotations on a medical coding task. |
LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals (2026.findings-acl)
Copied to clipboard
| Challenge: | Concept-based explanations quantify how high-level concepts influence model behavior . existing benchmarks rely on costly human-written counterfactuals that serves as imperfect proxy . |
| Approach: | They propose a framework for constructing datasets containing structural counterfactual pairs . they use a structured Causal Model to generate a concept-based explanation . |
| Outcome: | The proposed framework compares concept-based explanations to causal effects estimated from counterfactuals. |
Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations (2024.lrec-main)
Copied to clipboard
| Challenge: | We compare webcam-based eye-tracking recordings with human-annotated rationales to evaluate importance scores. |
| Approach: | They compare webcam-based eye-tracking recordings with attention-based importance scores for 4 different multilingual Transformer-based language models. |
| Outcome: | The proposed method is comparable to human rationales in linguistic analysis. |
DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications (2023.acl-long)
Copied to clipboard
| Challenge: | Several explainability methods have been shown to be brittle in the face of adversarial perturbations of their inputs in the image and generic textual domains. |
| Approach: | They propose to adapt existing attribution robustness estimation methods to take into account domain-specific plausibility and to train networks that display robust attributions. |
| Outcome: | The proposed methods are able to characterize domain-specific plausibility and provide robust explanations on biomedical datasets. |
The Anatomy of Evidence: An Investigation Into Explainable ICD Coding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing systems that use explainability methods have limited their effectiveness due to a lack of annotated data. |
| Approach: | They propose match measures and highlight success and failure cases to improve automatic medical coding. |
| Outcome: | The proposed models show that ground truth evidence aligns with code descriptions to a certain degree. |
Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting (2024.emnlp-main)
Copied to clipboard
Maxime Kayser, Bayar Menzat, Cornelius Emde, Bogdan Bercean, Alex Novak, Abdalá Morgado, Bartlomiej Papiez, Susanne Gaube, Thomas Lukasiewicz, Oana-Maria Camburu
| Challenge: | XAI models are being used in safety-critical domains, but their use is limited due to their limited transparency and insufficient model robustness. |
| Approach: | They evaluated visual, natural language and a combination of both modalities to examine how users use them. |
| Outcome: | The proposed model is more robust and transparent than previous models. |
Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing explainability methods for Large Language Models treat hidden states as static points in activation space, but they are saturated with polysemantic features. |
| Approach: | They propose a framework that shifts analysis from static activations to layer-wise geometric displacement. |
| Outcome: | The proposed framework outperforms existing explainability methods on commonsense reasoning, question answering, and toxicity detection benchmarks. |