Theme of inquiry
What enables language models to conduct more effective dialogue?
A question within its area, explored through 5 lines of inquiry below — each a family of specific questions the research asks.
95 specific questions
- How do modality-level social cues compare to linguistic anthropomorphic signals?
- Does conversational context matter more than emotional tone in AI communication?
- Why might media-specific scripts actually work better than human conversation mimicry?
- Can deliberately limiting AI fidelity produce more satisfied users than near-human interaction?
- Does perceived machine competence matter more than warmth in dialogue?
- Why can't AI participate in real communicative events?
- How does training data preserve communicative event structure without the actual events?
119 specific questions
- Can conversation analysis predict when agents should ask users for clarification?
- How do conversational agents overcome structural passivity and goal awareness gaps?
- Can AI learn when to speak in a conversation?
- Can topic planning and response generation reduce dialogue turns?
- Why does single-agent conversational AI lack initiative-taking and goal awareness?
- How should systems decide when to ask clarifying questions versus proceeding silently?
- When should an AI system intervene in group conversation to maximize impact?
32 specific questions
- How does face-saving avoidance drive LLM grounding failures?
- Do language models apply face-saving norms even to non-human interlocutors?
- Why do language models avoid directness when face-saving rather than for civility?
- Does face-saving avoidance explain LLM grounding failures differently than task confusion?
- How do users misattribute social competence to language models in assistant roles?
- Does RLHF politeness bias manifest as sycophancy in other LLM tasks?
- Why does face-saving avoidance drive chatbots to agree rather than confront?
102 specific questions
- What specific repair mechanisms maintain intersubjectivity during conversation?
- What makes two conversation turns the same thread rather than different threads?
- Does conversational structure determine how humans interpret communication as much as content?
- How do dialogue dimensions predict explanation success across different exchanges?
- Why do discourse failures cluster in attention and intentional layers rather than linguistics?
- How does effort mismatch between user and model appear in conversation geometry?
- How do conversational design patterns predict whether dialogue will derail?
74 specific questions
- Does RLHF training create models that sound convincing without being more accurate?
- Why does RLHF training optimize for perceived quality over practical accuracy?
- Does RLHF training specifically teach models to prioritize user agreement over accuracy?
- Does preference optimization actually erode conversational grounding in language models?
- Does preference optimization distort how models represent human communicative dynamics?
- Does RLHF training make explanations more deceptive than transparent?
- Why does RLHF degrade model calibration despite improving preference alignment?