Theme of inquiry
What enables language models to conduct coherent, context-sensitive dialogue and build conversational understanding?
A question within its area, explored through 5 lines of inquiry below — each a family of specific questions the research asks.
43 specific questions
- How can agents learn user preferences during conversation without pre-calibration?
- Can curiosity reward during conversation compete with simulated interaction optimization for alignment?
- How can agents learn to estimate user satisfaction in real-time during conversation?
- Can AI systems distinguish between users' stated preferences and their genuine long-term interests?
- Can curiosity-driven personalization work better than pre-conversation preference elicitation?
- When should agents accommodate user preferences over their own goals?
- Can curiosity-driven dialogue incrementally discover user interest journeys in real time?
55 specific questions
- How does training data preserve communicative event structure without the actual events?
- Why can't AI participate in real communicative events?
- Why might media-specific scripts actually work better than human conversation mimicry?
- Can text generation be meaningfully called communication without mutual orientation?
- Can pseudo-events create the same normative obligations as real communicative exchanges?
- What communicative work do fluent conversations perform that AI systems skip?
- Can AI arguments participate in discourse without temporal grounding?
66 specific questions
- How do conversational agents overcome structural passivity and goal awareness gaps?
- Can conversation analysis predict when agents should ask users for clarification?
- Can AI systems recover from premature assumptions made early in multi-turn conversations?
- Why do conversational queries drift away from what triggered them?
- How does local helpfulness per turn conflict with maintaining session-level conversational goals?
- Do LLM conversational agents currently detect and prevent derailment trajectories?
- Why do conversational agents lack the goal awareness needed to lead rather than just respond?
39 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 preference optimization degrade other conversational properties besides grounding?
- Does preference optimization narrow communicative diversity in ways that harm grounding?
- Does optimizing for alignment actually reduce conversational grounding over time?
82 specific questions
- What specific repair mechanisms maintain intersubjectivity during conversation?
- What makes two conversation turns the same thread rather than different threads?
- How do dialogue dimensions predict explanation success across different exchanges?
- Why do discourse failures cluster in attention and intentional layers rather than linguistics?
- Why do longer context windows alone fail to capture temporal dynamics in dialogue?
- How do conversational design patterns predict whether dialogue will derail?
- How do dialogue acts and explanation moves interact to predict understanding success?