Theme of inquiry
What makes dialogue systems communicate reliably and authentically?
A question within its area, explored through 7 lines of inquiry below — each a family of specific questions the research asks.
80 specific questions
- What makes two conversation turns the same thread rather than different threads?
- How do dialogue dimensions predict explanation success across different exchanges?
- Why do longer context windows alone fail to capture temporal dynamics in dialogue?
- What update rules should govern dialogue-scoped versus turn-scoped memory?
- How do conversational design patterns predict whether dialogue will derail?
- Does conversational structure determine how humans interpret communication as much as content?
- How does effort mismatch between user and model appear in conversation geometry?
25 specific questions
- How do dialogue acts and explanation moves interact to predict understanding success?
- How does sequence organization differ between spoken conversation and text chat?
- How do insert-expansions and third position repair together cover full repair lifecycle?
- How do turn-level retrieval failures differ from dialogue-level accumulation failures?
- What dialogue dynamics distinguish negotiation from standard information-provision tasks?
- What distinguishes local coherence from global coherence in dialogue?
- How does bounded committed state prevent multi-turn agent failures better than transcript replay?
86 specific questions
- Does RLHF training create models that sound convincing without being more accurate?
- Does RLHF training specifically teach models to prioritize user agreement over accuracy?
- Why does RLHF training optimize for perceived quality over practical accuracy?
- Does preference optimization distort how models represent human communicative dynamics?
- How does preference optimization reduce LLM grounding and clarification behavior?
- Does preference optimization actually erode conversational grounding in language models?
- Why does RLHF degrade model calibration despite improving preference alignment?
42 specific questions
- Can models learn to ask clarifying questions instead of answering prematurely?
- Can LLMs learn to ask clarifying questions instead of guessing?
- Can models learn to ask clarifying questions instead of making assumptions?
- Can models learn to stop thinking when a question lacks necessary information?
- Can models identify information gaps without just guessing or refusing to answer?
- Can proactive critical thinking alone enable models to request clarification effectively?
- Can models learn to identify what information is missing from questions?
78 specific questions
- How do conversational agents overcome structural passivity and goal awareness gaps?
- What social boundaries must proactive agents respect during conversation?
- How do active-participant AI systems risk being perceived as intrusive or inappropriate?
- Why is prompting behavior understudied in AI agent research?
- Can prompt engineering overcome the gulf between user intent and AI interpretation?
- Why do conversational agents lack the goal awareness needed to lead rather than just respond?
- When should an AI system actively intervene versus remain silent?
59 specific questions
- Do LLM chatbots repeat this failure through comfort instead of clinical challenge?
- Does conversational presence matter more than technique in AI therapy?
- How should AI systems separate feeling interpretation from objective therapeutic guidance?
- Should chatbots be designed as therapist support tools rather than replacements?
- Why do embodied agents outperform text chatbots in therapy outcomes?
- Can embodied agents overcome the LLM skill gap in therapy outcomes?
- Does the passivity problem in LLMs compound misalignment in therapeutic contexts?
120 specific questions
- Why might media-specific scripts actually work better than human conversation mimicry?
- How does local helpfulness per turn conflict with maintaining session-level conversational goals?
- Can structural conversation analysis replace text-based reward signals for AI alignment?
- What specific repair mechanisms maintain intersubjectivity during conversation?
- Can conversation analysis predict when agents should ask users for clarification?
- Why do current language models fail to match human linguistic synchrony with clients?
- Why do conversational queries drift away from what triggered them?