12 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…
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…
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…
Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels
Jonathan Grizou, Carlos de la Torre-Ortiz, Tuukka Ruotsalo
We consider the problem of recovering a mental target (e.g., an image of a face) that a participant has in mind from paired EEG (i.e., brain responses) and image (i.e., perceived f…
BrainLLM: Generative Language Decoding from Brain Recordings
Ziyi Ye, Qingyao Ai, Yiqun Liu +4
Generating human language through non-invasive brain-computer interfaces (BCIs) has the potential to unlock many applications, such as serving disabled patients and improving commu…