5 papers
Evaluating Sparse Autoencoders for Monosemantic Representation
Moghis Fereidouni, Muhammad Umair Haider, Peizhong Ju +1
A key barrier to interpreting large language models is polysemanticity, where neurons activate for multiple unrelated concepts. Sparse autoencoders (SAEs) have been proposed to mit…
A Framework for Generating Conversational Recommendation Datasets from Behavioral Interactions
Vinaik Chhetri, Yousaf Reza, Moghis Fereidouni +3
Modern recommendation systems typically follow two complementary paradigms: collaborative filtering, which models long-term user preferences from historical interactions, and conve…
INTERPOS: Interaction Rhythm Guided Positional Morphing for Mobile App Recommender Systems
M. H. Maqbool, Moghis Fereidouni, Umar Farooq +2
The mobile app market has expanded exponentially, offering millions of apps with diverse functionalities, yet research in mobile app recommendation remains limited. Traditional seq…
Evaluating and Enhancing Out-of-Domain Generalization of Task-Oriented Dialog Systems for Task Completion without Turn-level Dialog Annotations
Adib Mosharrof, Moghis Fereidouni, A. B. Siddique
Traditional task-oriented dialog (ToD) systems rely heavily on labor-intensive turn-level annotations, such as dialogue states and policy labels, for training. This work explores w…
Improving Multi-turn Task Completion in Task-Oriented Dialog Systems via Prompt Chaining and Fine-Grained Feedback
Moghis Fereidouni, Md Sajid Ahmed, Adib Mosharrof +1
Task-oriented dialog (TOD) systems facilitate users in accomplishing complex, multi-turn tasks through natural language. While instruction-tuned large language models (LLMs) have d…