2 papers
cs.AI2026
Towards Human-Level Book-Writing Capability
Jan Zierstek, Matteo Batelic, Maya Medjad +1
Large language models are optimized for instruction following and agentic tasks remain poorly aligned with the requirements of high-quality creative writing. We show that a purpose…
cs.CL2025
Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues
Maya Medjad, Hugo Imbert, Bruno Yun +2
Training task-oriented dialogue systems is both costly and time-consuming, due to the need for high-quality datasets encompassing diverse intents. Traditional methods depend on ext…