Theme of inquiry
How can dialogue systems develop robust grounding and natural human interaction?
A question within its area, explored through 8 lines of inquiry below — each a family of specific questions the research asks.
39 specific questions
- How do users update their partner models during ongoing conversation?
- What happens to user expectations as AI conversation quality improves?
- Does perceived machine competence matter more than warmth in dialogue?
- Can a virtual instance be individuated from its conversational context?
- How do casual conversational styles make AI seem more human?
- What would co-constructed identity between human and model dialogue look like?
- Do people treat conversational AI as social actors without conscious awareness?
29 specific questions
- How should conversational recommender systems balance task focus with rapport building?
- What other conversation structures besides mention order carry predictive information for recommendation?
- Does transforming critiques into preferences change how conversational recommenders should decide when to ask versus recommend?
- How much of conversational recommender progress comes from chasing flawed metrics?
- How can a single policy handle both asking preferences and recommending items?
- How do attribute-asking strategies depend on current confidence in candidate items?
- Why do bag-of-mentions models discard conversation order in the first place?
59 specific questions
- What makes two conversation turns the same thread rather than different threads?
- Why do longer context windows alone fail to capture temporal dynamics in dialogue?
- Does conversational structure determine how humans interpret communication as much as content?
- What update rules should govern dialogue-scoped versus turn-scoped memory?
- What structural updates prevent context collapse in evolving conversations?
- How do conversational design patterns predict whether dialogue will derail?
- Can discourse-level structure and conversational-level organization work together?
46 specific questions
- How do conversational agents overcome structural passivity and goal awareness gaps?
- When should an AI system actively intervene versus remain silent?
- What social boundaries must proactive agents respect during conversation?
- Why do conversational agents lack the goal awareness needed to lead rather than just respond?
- How do agents decide when to abstain from contributing?
- Can proactive AI agents deploy politeness strategies without appearing intrusive?
- How can agents learn when silence is better than intervention?
37 specific questions
- Why do current language models fail at linguistic synchrony with clients?
- Why do current language models fail to match human linguistic synchrony with clients?
- Why do current conversational AI systems fail to develop shared vocabulary with users?
- What communicative work do fluent conversations perform that AI systems skip?
- Why can't AI participate in real communicative events?
- Can real-time linguistic coordination tracking improve conversational AI quality?
- Why might media-specific scripts actually work better than human conversation mimicry?
37 specific questions
- What distinguishes static grounding that presumes understanding from dynamic grounding that builds it?
- Can static word-sharing create genuine communicative grounding between humans and models?
- Why do language models presume common ground rather than build it?
- Does social grounding in language improve through iterative human integration?
- Can language models develop genuine social grounding through human interaction?
- Why do language models presume common ground instead of building it?
- Can convention formation improve communicative grounding beyond word sharing?
71 specific questions
- How does local helpfulness per turn conflict with maintaining session-level conversational goals?
- Can curiosity reward during conversation compete with simulated interaction optimization for alignment?
- Can multi-turn conversations manipulate language model reasoning in similar ways to personas?
- Can structural conversation analysis replace text-based reward signals for AI alignment?
- How does conversational closure differ from genuine problem understanding?
- Can conversation analysis predict when agents should ask users for clarification?
- How can dialogue structure and trajectory predict social agent performance?
33 specific questions
- Does preference optimization actually erode conversational grounding in language models?
- Why does preference optimization reduce grounding behavior in language models?
- How does preference optimization reduce LLM grounding and clarification behavior?
- Does preference optimization distort how models represent human communicative dynamics?
- Does optimizing for alignment actually reduce conversational grounding over time?
- Does preference optimization degrade other conversational properties besides grounding?
- How does preference optimization erode the conversational grounding it aims to improve?