XAI

Papers

Can adversarial attacks by large language models be attributed? (pdf)
M. Cebrian, J.A. Telle
arXiv preprint, 2024

On a Combinatorial Problem Arising in Machine Teaching (pdf)
B. Håvardstun, J. Kratochvíl, J. Sunde, J.A. Telle
International Conference on Machine Learning (ICML), 2024

MAP- and MLE-Based Teaching (pdf)
H. Simon, J.A.Telle
Journal of Machine Learning Research (JMLR), 2024

Explainable LLM-powered RAG to tackle tasks in the unstructured-structured data spectrum (pdf)
D. Garigliotti
Special Session on LLMs at the International Semantic Web Conference (ISWC), 2024

EquinorQA: Large Language Models for Question Answering over proprietary data (pdf)
D. Garigliotti, B. Johansen, J. Vigerust Kallestad, S. Cho, C. Ferri
Conference on Prestigious Applications of Intelligent Systems (PAIS) co-located with the 27th European Conference on Artificial Intelligence (ECAI), 2024

Optimal Robust Simplifications for Explaining Time Series Classifications (pdf)
J.A. Telle, C. Ferri, B. Håvardstun
Explainable AI for Time Series and Data Streams Workshop (TempXAI) co-located with the European Conference on Machine Learning (ECML-PKDD), 2024

On the implications of data contamination for Information Retrieval systems (pdf)
D. Garigliotti
International Workshop on Data-Centric Artificial Intelligence (DEARING) co-located with the European Conference on Machine Learning (ECML-PKDD), 2024

Explaining LLM-based Question Answering via the self-interpretations of a model (pdf)
D. Garigliotti
International Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence (AIMLAI) co-located the European Conference on Machine Learning (ECML-PKDD), 2024

Automatic PDF Document Classification with Machine Learning (pdf)
S. Llácer Luna, D. Garigliotti, F. Martínez-Plumed, C. Ferri
Intelligent Data Engineering and Automated Learning (IDEAL) Conference, 2024

Entity Examples for Explainable Query Target Type Identification with LLMs (pdf)
D. Garigliotti
Intelligent Data Engineering and Automated Learning (IDEAL) Conference, 2024

Evaluating performance and trustworthiness of RAG systems for generating administrative text (pdf)
H. Sánchez Navalón, C. Monserrat Aranda, D. Garigliotti, C. Ferri
Intelligent Data Engineering and Automated Learning (IDEAL) Conference, 2024

On the Relevant Set of Contexts for Evaluating Retrieval-Augmented Generation Systems (pdf)
D. Garigliotti
Retrieval-Augmented Generation enabled by Knowledge Graphs workshop (RAGE-KG) co-located with the International Semantic Web Conference (ISWC), 2024

Retrieval-Augmented Generation for Query Target Type Identification (pdf)
D. Garigliotti
Retrieval-Augmented Generation enabled by Knowledge Graphs workshop (RAGE-KG) co-located with the International Semantic Web Conference (ISWC), 2024

Self-Explanatory Retrieval-Augmented Generation for SDG Evidence Identification (pdf)
D. Garigliotti
International Workshop on AI Services and Applications (AISA) co-located with the Conceptual Modeling (ER) Conference, 2024

On Data Contamination in Recommender Systems (pdf)
D. Garigliotti
Workshop on Risks, Opportunities, and Evaluation of Generative Models (ROEGEN), co-located with the ACM Conference on Recommender Systems (RecSys), 2024

Confounders in Instance Variation for the Analysis of Data Contamination (pdf)
B. Mehrbakhsh, D. Garigliotti, F. Martínez-Plumed, J. Hernández-Orallo
Contaminated Data Workshop (CONDA) co-located with the 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024

SDG target detection in environmental reports using Retrieval-augmented Generation with LLMs (pdf)
D. Garigliotti
Natural Language Processing meets Climate Change Workshop (ClimateNLP) co-located with the 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024

An Interactive Tool for Interpretability of Time Series Classification (video)
B. Håvardstun, C. Ferri, J.A. Telle
Demo Track of the European Conference on Machine Learning (ECML-PKDD), 2024

XAI for Time Series Classification: Evaluating the Benefits of Model Inspection for End-Users (pdf)
B. Håvardstun, C. Ferri, K. Flikka, J.A. Telle
World Conference on eXplainable Artificial Intelligence (xAI), 2024

When Redundancy Matters: Machine Teaching of Representations (pdf)
C. Ferri, D. Garigliotti, B. Håvardstun, J. Hernández-Orallo, J.A. Telle
arxiv preprint, 2024

A historical perspective of biomedical explainable AI research (pdf)
C. Ferri et al.
Patterns Journal, 2023

XAI with Machine Teaching when Humans Are (Not) Informed about the Irrelevant Features (pdf)
B. Håvardstun, C. Ferri, J. Hernández-Orallo, P. Parviainen, J.A. Telle
European Conference on Machine Learning (ECML-PKDD), 2023

Heuristic search of optimal machine teaching curricula (pdf)
M. Garcia-Piqueras, J. Hernández-Orallo
Machine Learning Journal, 1-32, 2023

Non-Cheating Teaching Revisited: A New Probabilistic Machine Teaching Model (pdf)
C. Ferri, J. Hernández-Orallo, J.A. Telle
International Joint Conference on Artificial Intelligence (IJCAI), 2022

On the trade-off between fidelity and teaching complexity (pdf)
B. Håvardstun, C. Ferri, J. Hernández-Orallo, P. Parviainen, J.A. Telle
11th International Workshop on Approaches and Applications of Inductive Programming (AAIP) co-located with the International Joint Conference on Learning and Reasoning (IJCLR), 2022

Conditional teaching size (pdf)
M. Garcia-Piqueras, J. Hernández-Orallo
arXiv preprint, 2021

Teaching and explanations: aligning priors between machines and humans (link)
J. Hernández-Orallo, C. Ferri
Human-Like Machine Intelligence, 171-198, 2021

Optimal Teaching Curricula with Compositional Simplicity Priors (pdf)
M. Garcia-Piqueras, J. Hernández-Orallo
European Conference on Machine Learning (ECML-PKDD), 2021

Finite and Confident Teaching in Expectation: Sampling from Infinite Concept Classes (pdf)
J. Hernández-Orallo, J.A. Telle
23rd European Conference on Artificial Intelligence (ECAI), 2020

Teaching explanations by examples (pdf)
C. Ferri, J. Hernández-Orallo, J.A. Telle
MI21-HLC Machine Intelligence workshop on Human-Like Computing, 2019

The Teaching Size: Computable Teachers and Learners for Universal Languages (link)
J.A. Telle, J. Hernández-Orallo, C. Ferri
Machine Learning Journal, 2019

Finite biased teaching with infinite concept classes (pdf)
J. Hernández-Orallo, J.A. Telle
arXiv preprint, 2018