Investigating Proactivity in Multimodal Task-Guidance Dialogues

MUDiC: A Dataset for Multi-User Dialogue and Collaboration in Chatbot Interaction

PAIR: A Pilot Dataset for Dual Perspective-based Video-Grounded Dialogue and Reconciliation

Collaborative dialogue in multi-agent settings often requires interlocutors to integrate partially overlapping perceptual information in order to construct a shared representation of a dynamic environment. We introduce PAIR, a pilot conversational corpus designed to examine how humans coordinate under systematic percep...

TalkFa: A Unified Benchmark for Farsi Dialogue Generation and Understanding

Experiments with six LLAMA and MISTRAL models show that LoRA substantially improves dialogue generation while requiring only 25-50% of the training data to recover over 90% of the final performance gains, and zero-shot evaluation with frontier LLMs shows that TalkFa remains a challenging benchmark.

The Illusion of Progress: Dialogue-Derived Signals for Proactive Intervention Timing in Student–GenAI Interaction

This work argues for a restraint-first intervention policy: systems should intervene not merely because dialogue appears active, but when sustained engagement fails to convert into observable enactment, while withholding intervention once concrete enactment cues are present.

A Unified Response Framework for Questions and Tutoring Dialogues

A unified framework that models both student responses to questions and tutor-posed subtasks during dialogues on a shared item response theory (IRT) scale is proposed and results show that the framework outperforms strong baselines on both question difficulty prediction and response correctness prediction.

Exploring Strategies for Conceptual Alignment in LLM-Based Human-Robot Dialogue

Successful conversations require speakers to align on conceptual understanding, a challenging but crucial task in human-robot interaction. With the increasing use of large language models for dialogue, robots move from passively acquiring human conceptualizations to actively shaping alignment. However, the design space...