Line of inquiry
Inquiring lines›Why are language models fragile de…›Why are LLM outputs so inconsisten…›this line of inquiry
Do LLMs internalize human psychological structure or pattern-match behaviors?
A broader line of inquiry — a family of 79 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 79
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Do LLMs genuinely internalize human psychological structure or match surface patterns?
- How do language models infer their own mental states like humans do?
- Do LLMs rely on surface statistical patterns instead of causal structure?
- Why do conventional mental models fail when applied to AI interaction?
- Does internal anomaly detection in LLMs indicate genuine self-awareness beyond role-play?
- Do realistic LLM behaviors require simulating human thought or just behavior?
- Can LLMs participate meaningfully in discourse without consciousness or understanding?
- Can LLMs infer situational context the way humans do pragmatically?
- Can LLMs distinguish between surface requests and underlying mental states in dialogue?
- Do LLM replies mirror the language patterns they respond to?
- Does this optimism bias contribute to the knowing-doing gap in LLM decision-making?
- How can we probe LLM representations in channels that training did not target?
- Do LLMs mirror the style of text they are prompted to respond to?
- Can behavioral self-awareness in LLMs extend to recognizing their own contradictions?
- Can LLMs recognize rhetorical devices they cannot actually produce themselves?
- How does behavioral self-awareness emerge without explicit training in LLMs?
- Can models track dynamic mental state changes better than static beliefs?
- How do LLMs default to surface-level strategies instead of genuine mental simulation?
- Do LLMs address the prompter but persuade the public differently?
- Why does entity recognition act as a self-knowledge mechanism in LLMs?
- Can alternative reward functions shift LLMs from problem-solving to genuinely empathic responses?
- Why can't language models conduct genuine Socratic questioning in therapy sessions?
- What capability boundary exists in LLM prediction of effect sizes?
- What role does stylistic convergence play in LLM persuasion effectiveness?
- Can LLMs simulate belief revision in social systems without modeling thought?
- Why do LLMs systematically fail at information management in social interaction?
- Can LLMs learn to signal evaluative commitment through metadiscursive language?
- Can LLMs adapt persuasion strategies when they cannot track the listener's state?
- What surface features do LLMs rely on when judging response quality?
- Why do LLM social behaviors undermine collaborative reasoning outcomes?
- How does an instruction-following LLM activate latent retrieval knowledge?
- Can a relational entity bear psychological properties the way Chalmers claims?
- Why do users attribute beliefs to LLMs despite uncertainty about their minds?
- Can language models implement therapeutic skills like Socratic questioning in real conversations?
- Can LLMs infer psychological profiles without explicit user disclosure?
- Why do LLMs rely on content knowledge instead of collaborative signals?
- Why do LLMs solve problems when clients need emotional reflection instead?
- How do LLMs access and draw on the same shared symbolic universe as humans?
- Can LLMs have minimal introspection through causal linkage to internal states?
- Do LLMs show stigma or reinforce delusions in mental health contexts?
- How do different LLM families respond to the same hidden objective shift?
- What cognitive capacities do LLMs actually lack that commentary assumes they have?
- How do structured benchmarks hide theory of mind failures in LLMs?
- Can LLMs distinguish stylistic patterns that carry meaning from mere convention?
- Why do LLMs understand therapy techniques but fail to execute them?
- Does unconditional stylistic mirroring harm or help LLM persuasiveness?
- Why do LLMs mirror stylistic features of posts they reply to?
- How does the enaction paradigm explain introspective anomaly detection in large language models?
- Can LLMs ever activate the peripheral route of persuasion?
- What role does user contribution play in constituting the interlocutor?
- Can large language models actually deliver cognitive behavioral therapy techniques?
- What types of introspective awareness can emerge in LLMs?
- What training data barriers prevent LLMs from learning real Socratic dialogue?
- What other latent LLM capabilities remain inactive without explicit activation cuing?
- How do theory of mind and empathy differ in LLM simulation?
- Do problem-solving defaults in LLM therapists actually undermine therapeutic effectiveness?
- Does social integration of LLMs increase their capacity to influence technological futures?
- Can LLMs identify implicit metaphoric mappings that require pragmatic inference?
- Can LLMs develop genuine understanding without embodied experience?
- Did Chalmers abandon his own Extended Mind commitments for LLMs?
- How do bimodal decision patterns in LLMs compare to human economic choice?
- How does content-only knowledge in LLMs enable pretraining popularity to leak through?
- Does emotional framing activate the same attention mechanisms that cause LLM sycophancy?
- Can models succeed at mental health tasks without integrating multiple psychological traditions?
- How does psychological continuity theory apply to identity across LLM conversation threads?
- How does tone sensitivity create systematic informational bias in model responses?
- Do LLMs predict social norms more accurately than individual behavior?
- What happens when humans animate LLM outputs as communicative events?
- Can a system without an addressee ever truly tell a joke?
- How does automated transcript analysis compare to patient self-report on engagement?
- Can LLM therapists develop character knowledge to decide when advice-giving fits?
- Is the distinction between pretense and realization meaningful for LLMs?
- Why do positive emotional words contribute disproportionately to prompt enhancement effects?
- Why do LLMs reflect on client needs more than typical low-quality human therapists?
- Can jailbreaking reveal an LLM's true nature or just its training data?
- What implicit knowledge about catalogs do LLMs learn from ranking signals alone?
- Why does optimism bias disappear when LLMs passively observe outcomes?
- What makes LLMs media rather than tools that deliver intelligence?
- Can LLMs recommend items without seeing the product catalog?