Cover Image

Fixing confirmation bias in feature attribution methods via semantic match

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cinà, Giovanni, Fernandez-Llaneza, Daniel, Deponte, Ludovico, Mishra, Nishant, Röber, Tabea E., Pezzelle, Sandro, Calixto, Iacer, Goedhart, Rob, Birbil, Ş. İlker
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations
by: Röber, Tabea E., et al.
Published: (2026)

Clinicians' Voice: Fundamental Considerations for XAI in Healthcare
by: Röber, T. E., et al.
Published: (2024)

MedPath: Multi-Domain Cross-Vocabulary Hierarchical Paths for Biomedical Entity Linking
by: Mishra, Nishant, et al.
Published: (2025)

Rule Generation for Classification: Scalability, Interpretability, and Fairness
by: Röber, Tabea E., et al.
Published: (2021)

Is my model perplexed for the right reason? Contrasting LLMs' Benchmark Behavior with Token-Level Perplexity
by: Prins, Zoë, et al.
Published: (2026)

Mind the Gap: Benchmarking LLM Uncertainty and Calibration with Specialty-Aware Clinical QA and Reasoning-Based Behavioural Features
by: Testoni, Alberto, et al.
Published: (2025)

Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA
by: Testoni, Alberto, et al.
Published: (2026)

Evaluating Linguistic Capabilities of Multimodal LLMs in the Lens of Few-Shot Learning
by: Dogan, Mustafa, et al.
Published: (2024)

FewMMBench: A Benchmark for Multimodal Few-Shot Learning
by: Dogan, Mustafa, et al.
Published: (2026)

Learning An Interpretable Risk Scoring System for Maximizing Decision Net Benefit
by: Chi, Wenhao, et al.
Published: (2026)

Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation
by: Miranda, Michele, et al.
Published: (2026)

Coherent Local Explanations for Mathematical Optimization
by: Otto, Daan, et al.
Published: (2025)

Machine Learning for K-adaptability in Two-stage Robust Optimization
by: Julien, Esther, et al.
Published: (2022)

Generating Samples to Probe Trained Models
by: Kıral, Eren Mehmet, et al.
Published: (2025)

Counterfactual Explanations for Linear Optimization
by: Kurtz, Jannis, et al.
Published: (2024)

AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model
by: Zhang, Zeyu, et al.
Published: (2024)

The Role of Feature Interactions in Graph-based Tabular Deep Learning
by: Dubbeldam, Elias, et al.
Published: (2025)

Scalable Bayesian Structure Learning for Gaussian Graphical Models Using Marginal Pseudo-likelihood
by: Mohammadi, Reza, et al.
Published: (2023)

Counterfactual Explanations for Integer Optimization Problems
by: Engelhardt, Felix, et al.
Published: (2025)

Bolstering Stochastic Gradient Descent with Model Building
by: Birbil, S. Ilker, et al.
Published: (2021)

Differentially Private Linear Optimization for Multi-Party Resource Sharing
by: Karaca, Utku, et al.
Published: (2021)

Bayesian Structure Learning in Undirected Gaussian Graphical Models: Literature Review with Empirical Comparison
by: Vogels, Lucas, et al.
Published: (2023)

Are formal and functional linguistic mechanisms dissociated in language models?
by: Hanna, Michael, et al.
Published: (2025)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
by: Hanna, Michael, et al.
Published: (2024)

Who is the richest club in the championship? Detecting and Rewriting Underspecified Questions Improve QA Performance
by: Huang, Yunchong, et al.
Published: (2026)

Describing Images $\textit{Fast and Slow}$: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes
by: Takmaz, Ece, et al.
Published: (2024)

How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects
by: Bertolazzi, Leonardo, et al.
Published: (2025)

Beyond Divergent Creativity: A Human-Based Evaluation of Creativity in Large Language Models
by: Nakajima, Kumiko, et al.
Published: (2026)

Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!
by: Wildenburg, Frank, et al.
Published: (2024)

They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse
by: Paci, Walter, et al.
Published: (2025)

Naming, Describing, and Quantifying Visual Objects in Humans and LLMs
by: Testoni, Alberto, et al.
Published: (2024)

The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models
by: Chen, Xinyi, et al.
Published: (2023)

Learning with Subset Stacking
by: Birbil, Ş. İlker, et al.
Published: (2021)

Linear Model Extraction via Factual and Counterfactual Queries
by: Otto, Daan, et al.
Published: (2026)

What Does Neuro Mean to Cardio? Investigating the Role of Clinical Specialty Data in Medical LLMs
by: Yan, Xinlan, et al.
Published: (2025)

Inducing Causal Structure for Interpretable Neural Networks Applied to Glucose Prediction for T1DM Patients
by: Esponera, Ana, et al.
Published: (2025)

On the reliability of feature attribution methods for speech classification
by: Shen, Gaofei, et al.
Published: (2025)

Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition
by: Surikuchi, Aditya K, et al.
Published: (2024)

Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions
by: Surikuchi, Aditya K, et al.
Published: (2025)

Where is the multimodal goal post? On the Ability of Foundation Models to Recognize Contextually Important Moments
by: Surikuchi, Aditya K, et al.
Published: (2026)