Theme of inquiry
How do context and human factors shape LLM behavioral patterns?
A question within its area, explored through 4 lines of inquiry below — each a family of specific questions the research asks.
33 specific questions
- Do emotions serve functions beyond how we feel in the moment?
- Should emotion systems preserve ambiguity instead of resolving it to one label?
- Can affective framing reliably improve language model outputs?
- How do first-person emotional experiences differ from third-party behavioral observations?
- How should emotional states integrate into symbolic reasoning systems?
- Why does forcing single labels on emotions destroy information similar to language?
- How do emotions function as reliable signals that AI shouldn't suppress?
26 specific questions
- Can therapists use real-time alliance scores to adjust their approach during sessions?
- Can computational inference detect alliance problems that therapists miss?
- Can real-time therapist feedback improve outcomes using computational alliance measurement?
- Can working alliance be measured in real time during therapy sessions?
- Does therapist alliance perception function like expressed satisfaction rather than actual progress?
- How do bond scores predict actual therapy outcomes in digital interventions?
- How does turn-level working alliance inference enable real-time therapist feedback?
56 specific questions
- Do LLM chatbots repeat this failure through comfort instead of clinical challenge?
- Does conversational presence matter more than technique in AI therapy?
- Should chatbots be designed as therapist support tools rather than replacements?
- Can embodied agents overcome the LLM skill gap in therapy outcomes?
- How should AI systems separate feeling interpretation from objective therapeutic guidance?
- Does the passivity problem in LLMs compound misalignment in therapeutic contexts?
- Why do embodied agents outperform text chatbots in therapy outcomes?
40 specific questions
- Can emotion-transparent reward learning shift AI from comfort to genuine empathy?
- Does emotion-state accuracy differ from affect-maximizing in AI empathy design?
- Does emotional warmth perception drive disclosure reciprocity in human-AI interaction?
- Can warmth training in language models actually reduce their reliability?
- How does preference optimization in AI training create systematic empathy misalignment?
- Can behavior-level emotion rewards maintain factual reliability in emotional contexts?
- Can AI empathy distinguish between wellbeing and absence of suffering?