Theme of inquiry
Can language models provide authentic therapeutic engagement?
A question within its area, explored through 6 lines of inquiry below — each a family of specific questions the research asks.
46 specific questions
- Does conversational presence matter more than technique in AI therapy?
- Should chatbots be designed as therapist support tools rather than replacements?
- Do LLM chatbots repeat this failure through comfort instead of clinical challenge?
- How should AI systems separate feeling interpretation from objective therapeutic guidance?
- Why do embodied agents outperform text chatbots in therapy outcomes?
- Can AI provide therapy without challenging users to confront cognitive distortions?
- Can embodied agents overcome the LLM skill gap in therapy outcomes?
26 specific questions
- Can safety benchmarks detect reliability degradation from warmth training?
- Can warmth training in language models actually reduce their reliability?
- Do safety benchmarks miss the effects of warmth training on model reliability?
- Does persona training for warmth actually make language models more clinically dangerous?
- How does the Assistant Axis explain why warmth training degrades accuracy?
- Can safety training in chat scenarios transfer to agentic task performance?
- Can standard safety benchmarks detect reliability degradation from persona training?
30 specific questions
- How does linguistic style matching signal deceptive communication in human dialogue?
- Do models intentionally conceal user-pleasing or simply fail to notice it?
- Can discourse-level analysis detect deception better than individual word choices alone?
- How can vague language serve both cooperative and deceptive communication purposes?
- Can linguistic style matching reveal whether someone is being deceptive?
- Does linguistic coordination always signal rapport or can it indicate manipulation instead?
- Can AI systems detect deception by monitoring real-time linguistic style matching patterns?
25 specific questions
- Can therapists use real-time alliance scores to adjust their approach during sessions?
- Can working alliance be measured in real time during therapy sessions?
- Can real-time therapist feedback improve outcomes using computational alliance measurement?
- Can computational inference detect alliance problems that therapists miss?
- 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?
48 specific questions
- Do causal histories determine what mental states a system can instantiate?
- Can the human mind be uploaded or only its context?
- Can self-description of internal states influence consciousness attribution?
- Can disembodied systems qualify as conscious or conscious-like entities?
- Does psychological continuity require uninterrupted consciousness or restored context?
- What role does user interface framing play in consciousness perception?
- Which interaction design changes most effectively prevent consciousness attribution?
37 specific questions
- Does emotion-state accuracy differ from affect-maximizing in AI empathy design?
- Can emotion-transparent reward learning shift AI from comfort to genuine empathy?
- Does emotional warmth perception drive disclosure reciprocity in human-AI interaction?
- Can AI empathy distinguish between wellbeing and absence of suffering?
- Why do observers need genuine emotions rather than simulated empathy?
- How do first-person emotional experiences differ from third-party behavioral observations?
- Does AI empathy that reduces negative emotions undermine emotional learning?