4 papers
Do Factual Recall Mechanisms Carry over from Text to Speech in Multimodal Language Models?
Luca Modica, Filip Landin, Mehrdad Farahani +3
In recent years, several Speech Language Models (SLMs) that represent speech and written text jointly have been presented. The question then emerges about how model-internal mechan…
To Copy or Not to Copy: Copying Is Easier to Induce Than Recall
Mehrdad Farahani, Franziska Penzkofer, Richard Johansson
Language models used in retrieval-augmented settings must arbitrate between parametric knowledge stored in their weights and contextual information in the prompt. This work present…
Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models
Mehrdad Farahani, Richard Johansson
Generative language models often struggle with specialized or less-discussed knowledge. A potential solution is found in Retrieval-Augmented Generation (RAG) models which act like…
An Empirical Study of Multitask Learning to Improve Open Domain Dialogue Systems
Mehrdad Farahani, Richard Johansson
Autoregressive models used to generate responses in open-domain dialogue systems often struggle to take long-term context into account and to maintain consistency over a dialogue.…