Theme of inquiry
How do language models maintain conversational coherence through grounding?
A question within its area, explored through 6 lines of inquiry below — each a family of specific questions the research asks.
71 specific questions
- What specific repair mechanisms maintain intersubjectivity during conversation?
- Why do longer context windows alone fail to capture temporal dynamics in dialogue?
- Why do discourse failures cluster in attention and intentional layers rather than linguistics?
- How do dialogue dimensions predict explanation success across different exchanges?
- What makes two conversation turns the same thread rather than different threads?
- What update rules should govern dialogue-scoped versus turn-scoped memory?
- Why do conversational queries drift away from what triggered them?
78 specific questions
- Why can't AI participate in real communicative events?
- Why might media-specific scripts actually work better than human conversation mimicry?
- Does perceived machine competence matter more than warmth in dialogue?
- How does training data preserve communicative event structure without the actual events?
- Can deliberately limiting AI fidelity produce more satisfied users than near-human interaction?
- Why do people evaluate machines against human communication standards?
- Why should AI communication design follow human communication norms?
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?
- Why do conversational agents lack the goal awareness needed to lead rather than just respond?
- What makes conversational agents passive compared to goal-directed colleagues?
- Can passive conversational agents initiate topics or only respond to users?
- How do insert-expansions help systems probe users before silently diverging?
- Can topic planning and response generation reduce dialogue turns?
29 specific questions
- Does preference optimization actually erode conversational grounding in language models?
- Why does preference optimization reduce grounding behavior in language models?
- Does preference optimization degrade other conversational properties besides grounding?
- How does preference optimization reduce LLM grounding and clarification behavior?
- How does preference optimization erode the conversational grounding it aims to improve?
- Does preference optimization distort how models represent human communicative dynamics?
- How does preference optimization weaken conversational grounding in LLMs?
6 specific questions
- Why does static grounding prevent AI systems from supporting dialectical reconciliation?
- Why can't static grounding alone close the gap between agreement and understanding?
- What is the difference between static and dynamic grounding in dialogue?
- What role does dynamic grounding play in achieving real mutual understanding?
- What makes grounding acts essential to conversational reliability?
- Why is false punditry essentially static grounding applied to public commentary?
47 specific questions
- How does linguistic coordination build shared reference between conversational partners?
- How does monological training on text differ from dialogical training in conversation?
- Does conversational structure determine how humans interpret communication as much as content?
- Why does joint attention matter for acquiring linguistic meaning?
- How does unilateral interpretation differ from mutual communicative uptake?
- How does lexical entrainment depend on selective frame-activation in conversation?
- How does shared reference and grounding affect assumption detection in dialogue?