58 citations · 186 across the 30 of their papers we have counts for
30 papers
Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration
Pietro Tropeano, Maria Maistro, Tuukka Ruotsalo +1
Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of their accuracy. As attention…
Can Fairness Be Prompted? Prompt-Based Debiasing Strategies in High-Stakes Recommendations
Mihaela Rotar, Theresia Veronika Rampisela, Maria Maistro
Large Language Models (LLMs) can infer sensitive attributes such as gender or age from indirect cues like names and pronouns, potentially biasing recommendations. While several deb…
Post-Training Denoising of User Profiles with LLMs in Collaborative Filtering Recommendation
Ervin Dervishaj, Maria Maistro, Tuukka Ruotsalo +1
Implicit feedback -- the main data source for training Recommender Systems (RSs) -- is inherently noisy and has been shown to negatively affect recommendation effectiveness. Denois…
Measuring Individual User Fairness with User Similarity and Effectiveness Disparity
Theresia Veronika Rampisela, Maria Maistro, Tuukka Ruotsalo +1
Individual user fairness is commonly understood as treating similar users similarly. In Recommender Systems (RSs), several evaluation measures exist for quantifying individual user…
How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
Shivam Adarsh, Maria Maistro, Christina Lioma
Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations. These vectors, also known as truth vectors, have been studie…
The Quest for Reliable Metrics of Responsible AI
Theresia Veronika Rampisela, Maria Maistro, Tuukka Ruotsalo +1
The development of Artificial Intelligence (AI), including AI in Science (AIS), should be done following the principles of responsible AI. Progress in responsible AI is often quant…
Stairway to Fairness: Connecting Group and Individual Fairness
Theresia Veronika Rampisela, Maria Maistro, Tuukka Ruotsalo +2
Fairness in recommender systems (RSs) is commonly categorised into group fairness and individual fairness. However, there is no established scientific understanding of the relation…
Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
Joakim Edin, Casper L. Christensen, Róbert Csordás +5
Circuit localization methods aim to identify the subset of model components responsible for specific behaviors in large language models, enabling detailed mechanistic analysis. Mos…
As easy as PIE: understanding when pruning causes language models to disagree
Pietro Tropeano, Maria Maistro, Tuukka Ruotsalo +1
Language Model (LM) pruning compresses the model by removing weights, nodes, or other parts of its architecture. Typically, pruning focuses on the resulting efficiency gains at the…
Joint Evaluation of Fairness and Relevance in Recommender Systems with Pareto Frontier
Theresia Veronika Rampisela, Tuukka Ruotsalo, Maria Maistro +1
Fairness and relevance are two important aspects of recommender systems (RSs). Typically, they are evaluated either (i) separately by individual measures of fairness and relevance,…
Are Representation Disentanglement and Interpretability Linked in Recommendation Models? A Critical Review and Reproducibility Study
Ervin Dervishaj, Tuukka Ruotsalo, Maria Maistro +1
Unsupervised learning of disentangled representations has been closely tied to enhancing the representation intepretability of Recommender Systems (RSs). This has been achieved by…
A Reality Check on Context Utilisation for Retrieval-Augmented Generation
Lovisa Hagström, Sara Vera Marjanović, Haeun Yu +5
Retrieval-augmented generation (RAG) helps address the limitations of parametric knowledge embedded within a language model (LM). In real world settings, retrieved information can…
Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability
Joakim Edin, Andreas Geert Motzfeldt, Casper L. Christensen +3
Deep neural network predictions are notoriously difficult to interpret. Feature attribution methods aim to explain these predictions by identifying the contribution of each input f…
DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
Sara Vera Marjanović, Haeun Yu, Pepa Atanasova +3
Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated k…
An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records
Joakim Edin, Maria Maistro, Lars Maaløe +3
Electronic healthcare records are vital for patient safety as they document conditions, plans, and procedures in both free text and medical codes. Language models have significantl…
Can We Trust Recommender System Fairness Evaluation? The Role of Fairness and Relevance
Theresia Veronika Rampisela, Tuukka Ruotsalo, Maria Maistro +1
Relevance and fairness are two major objectives of recommender systems (RSs). Recent work proposes measures of RS fairness that are either independent from relevance (fairness-only…
Dataset and Models for Item Recommendation Using Multi-Modal User Interactions
Simone Borg Bruun, Krisztian Balog, Maria Maistro
While recommender systems with multi-modal item representations (image, audio, and text), have been widely explored, learning recommendations from multi-modal user interactions (e.…
Recommending Target Actions Outside Sessions in the Data-poor Insurance Domain
Simone Borg Bruun, Christina Lioma, Maria Maistro
Providing personalized recommendations for insurance products is particularly challenging due to the intrinsic and distinctive features of the insurance domain. First, unlike more…
Evaluation Measures of Individual Item Fairness for Recommender Systems: A Critical Study
Theresia Veronika Rampisela, Maria Maistro, Tuukka Ruotsalo +1
Fairness is an emerging and challenging topic in recommender systems. In recent years, various ways of evaluating and therefore improving fairness have emerged. In this study, we e…
Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study
Joakim Edin, Alexander Junge, Jakob D. Havtorn +4
Medical coding is the task of assigning medical codes to clinical free-text documentation. Healthcare professionals manually assign such codes to track patient diagnoses and treatm…
Graph-based Recommendation for Sparse and Heterogeneous User Interactions
Simone Borg Bruun, Kacper Kenji Lesniak, Mirko Biasini +4
Recommender system research has oftentimes focused on approaches that operate on large-scale datasets containing millions of user interactions. However, many small businesses strug…
FullBrain: a Social E-learning Platform
Mirko Biasini, Vittorio Carmignani, Nicola Ferro +3
We present FullBrain, a social e-learning platform where students share and track their knowledge. FullBrain users can post notes, ask questions and share learning resources in ded…
Principled Multi-Aspect Evaluation Measures of Rankings
Maria Maistro, Lucas Chaves Lima, Jakob Grue Simonsen +1
Information Retrieval evaluation has traditionally focused on defining principled ways of assessing the relevance of a ranked list of documents with respect to a query. Several met…
Learning Recommendations from User Actions in the Item-poor Insurance Domain
Simone Borg Bruun, Maria Maistro, Christina Lioma
While personalised recommendations are successful in domains like retail, where large volumes of user feedback on items are available, the generation of automatic recommendations i…