activity
20242026
collaborators

8 papers

cs.CL2026

In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads

Charlotte Pouw, Hosein Mohebbi, Afra Alishahi +1

In-Context Learning (ICL) has been extensively studied in text-only Language Models, but remains largely unexplored in the speech domain. Here, we investigate how linguistic and ac…

cs.CL2026

Tracking the emergence of linguistic structure in self-supervised models learning from speech

Marianne de Heer Kloots, Martijn Bentum, Hosein Mohebbi +3

Self-supervised speech models learn effective representations of spoken language, which have been shown to reflect various aspects of linguistic structure. But when does such struc…

cs.CL2026

Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures

Chiara Manna, Hosein Mohebbi, Afra Alishahi +2

While Large Language Models achieve state-of-the-art results across a wide range of NLP tasks, they remain prone to systematic biases. Among these, gender bias is particularly sali…

cs.CL2025

Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models

Dana Arad, Yonatan Belinkov, Hanjie Chen +5

Mechanistic interpretability (MI) seeks to uncover how language models (LMs) implement specific behaviors, yet measuring progress in MI remains challenging. The recently released M…

cs.CL2025

What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training

Marianne de Heer Kloots, Hosein Mohebbi, Charlotte Pouw +3

How language-specific are speech representations learned by self-supervised models? Existing work has shown that a range of linguistic features can be successfully decoded from end…

cs.CL2025

On the reliability of feature attribution methods for speech classification

Gaofei Shen, Hosein Mohebbi, Arianna Bisazza +2

As the capabilities of large-scale pre-trained models evolve, understanding the determinants of their outputs becomes more important. Feature attribution aims to reveal which parts…