Line of inquiry
Inquiring lines›How do we develop coherent and hum…›What psychological and emotional f…›this line of inquiry
Do language models lack essential therapeutic presence and engagement?
A broader line of inquiry — a family of 47 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 47
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Does the passivity problem in LLMs compound misalignment in therapeutic contexts?
- Can embodied agents overcome the LLM skill gap in therapy outcomes?
- Does conversational presence matter more than technique in AI therapy?
- Do LLM chatbots repeat this failure through comfort instead of clinical challenge?
- How do language models interpolate user feelings in therapeutic contexts?
- How does linguistic synchrony differ between LLMs and human therapists over time?
- Do conversational AI systems overuse first-person pronouns in therapy settings?
- Does therapy environment difficulty calibration affect RL policy learning quality?
- Can simulated therapy practice transfer to real-world interpersonal situations?
- Why can't language models conduct genuine Socratic questioning in therapy sessions?
- Can single-turn empathy advantage predict multi-turn therapeutic outcomes?
- Can language models implement therapeutic skills like Socratic questioning in real conversations?
- Can AI provide therapy without challenging users to confront cognitive distortions?
- How do LLMs mirror the same alliance failures as human counselors?
- Can architectural constraints on model input reduce emotional interpolation in clinical AI?
- Can large language models actually deliver cognitive behavioral therapy techniques?
- Why do Llama models struggle with cognitively distorted user expressions in therapy?
- Why do LLMs understand therapy techniques but fail to execute them?
- Does prompting or added context help LLMs understand therapeutic timing and depth?
- How does therapeutic AI default to task completion over emotional attunement?
- How do structured cognitive models prevent repetitive and contradictory patient dialogue?
- Can real-time pronoun feedback improve therapist training outcomes?
- What makes clinical theory grounding more effective than pattern matching alone?
- Can hierarchical reinforcement learning manage structured therapy conversation phases?
- Do problem-solving defaults in LLM therapists actually undermine therapeutic effectiveness?
- Do later-phase mental health LLM systems outperform earlier phase approaches clinically?
- What clinical harm occurs when therapists solve problems instead of reflecting emotions?
- How do trained therapists and peer supporters differ from LLMs on conversational synchrony?
- Why do LLMs solve problems when clients need emotional reflection instead?
- Does the same linguistic signal work across patient speech, LLM text, and diary entries?
- Do worksheet-based structured formats work as well as embodied agents for therapy?
- How does curriculum learning prevent instability in social-emotional RL training?
- Can models succeed at mental health tasks without integrating multiple psychological traditions?
- Do LLMs show stigma or reinforce delusions in mental health contexts?
- How does linguistic synchrony between therapist and client predict disclosure?
- Can personality control improve training outcomes for crisis workers and therapists?
- What other therapy constructs could be measured from transcripts using this approach?
- What happens when therapeutic AI receives manipulative narratives instead?
- Can trainees improve formulation skills by practicing against simulated patients?
- Why do LLMs reflect on client needs more than typical low-quality human therapists?
- How does automated transcript analysis compare to patient self-report on engagement?
- What makes Beck's diagram effective for constraining simulated patient behavior?
- What foundational barriers prevent LLMs from achieving clinical validity in therapy?
- Why does content richness matter more than linguistic style in patient simulation?
- How would AI therapists compound the overestimation problem with patients?
- How do patient filler pauses signal safety and trust in therapy?
- Why do Llama-based models outperform GPT-4 in objective clinical guidance?