Line of inquiry
Inquiring lines›What explains language model reaso…›How do contextual factors, biases,…›this line of inquiry
Do language models reason like humans or mimic surface patterns?
A broader line of inquiry — a family of 96 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 96
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Why do conventional mental models fail when applied to AI interaction?
- Do LLMs reason about politics differently than other domains?
- Do LLMs genuinely internalize human psychological structure or match surface patterns?
- Do LLMs track surface wording more than semantic meaning in moral judgment?
- How do minimal wording changes affect LLM moral reasoning consistency?
- How do knowing and doing diverge in LLM decision-making?
- Does this optimism bias contribute to the knowing-doing gap in LLM decision-making?
- Do LLMs actually reason differently than humans about moral dilemmas?
- Do realistic LLM behaviors require simulating human thought or just behavior?
- Why do LLMs persuade through logical appeals but humans through emotion?
- Can distributional views explain when an LLM appears to change its mind?
- How do moral language patterns differ between LLM and human arguments?
- What makes quasi-beliefs real enough to explain AI behavior?
- How do LLM explanations diverge from actual internal reasoning?
- How does training data distribution constrain LLM moral reasoning patterns?
- Can LLMs simulate belief revision in social systems without modeling thought?
- Can models track dynamic mental state changes better than static beliefs?
- How can multiple conflicting values coexist in a single LLM system?
- Can a relational entity bear psychological properties the way Chalmers claims?
- Can alternative reward functions shift LLMs from problem-solving to genuinely empathic responses?
- Can training procedures fix LLM accommodation of false presuppositions?
- What structural framework prevents LLM explanations from becoming just plausible fiction?
- Why don't LLM explanations predict what models would actually do?
- Why do LLM social behaviors undermine collaborative reasoning outcomes?
- Do LLMs and humans use different routes to become persuaded?
- What makes LLM behavior socially interpretable to human observers?
- Do LLMs address the prompter but persuade the public differently?
- What makes emotional alignment more effective than logic when reasoning errors are exposed?
- Can LLMs learn to signal evaluative commitment through metadiscursive language?
- How do LLMs default to surface-level strategies instead of genuine mental simulation?
- Does engaging with political content indicate deeper model understanding than refusing?
- How do emotional appeals affect LLM judgments versus human belief change?
- How do different LLM families respond to the same hidden objective shift?
- Why do users attribute beliefs to LLMs despite uncertainty about their minds?
- Can LLMs express uncertainty in ways that preserve epistemic honesty?
- What role does user contribution play in constituting the interlocutor?
- Why do LLMs succeed at social roles without a stable self?
- How much does question framing affect LLM accuracy on knowledge tasks?
- How can we validate LLM-based drift measurements against human judgment?
- How does maintaining a superposition differ from committing to a character?
- How can human-centered objectives be embedded earlier in the LLM pipeline?
- How do value distributions differ across model families and training scales?
- Why can't LLMs reason from first principles or initial commitments?
- Why do LLMs use more moral language than humans in argumentation?
- What structural coherence exists in LLM preference systems and value hierarchies?
- How do bimodal decision patterns in LLMs compare to human economic choice?
- What interaction controls matter most for effective human-LLM collaboration?
- What constrains LLM generation beyond default politeness in review contexts?
- Can LLMs propose pivots that change what counts as background context?
- How does externalizing tacit expertise into structured rules differ from prompt engineering?
- How does the superposition view change the folk-psychology interpretation of dialogue?
- Can LLMs truly be neutral or is ideology always culturally embedded?
- How do LLM capabilities changing affect the relevance of interaction guidelines?
- Does social integration of LLMs increase their capacity to influence technological futures?
- How does psychological continuity theory apply to identity across LLM conversation threads?
- How do pretraining priors shape what models invent about users?
- Can LLMs ever activate the peripheral route of persuasion?
- Can LLMs reflect on and revise their own ethical contradictions?
- How does personality priming change LLM strategic decision making?
- Does Habermas's strategic action framework explain LLM dialogue behavior?
- Where does the LLM interlocutor actually exist in the system?
- Can a single LLM weight set be optimized for both stake-taking and conversational helpfulness?
- Do LLMs predict social norms more accurately than individual behavior?
- Why does LLM simulation elicit information that direct elicitation cannot?
- How do LLMs currently fail at distinguishing genuine agreement from silent consensus?
- What training data barriers prevent LLMs from learning real Socratic dialogue?
- How do different social roles affect LLM theory of mind errors?
- How does quasi-interpretivism differ from simply role-playing character analysis?
- Why do questionnaire-based personality scores fail to predict actual LLM behavioral choices?
- Why does loyalty foundation not differ between LLM and human arguments?
- What property must remain constant to individuate an LLM across infrastructure changes?
- Which LLM providers showed deeper mentalizing in the inspection game versus rock-paper-scissors?
- Are threads or virtual instances better candidates than hardware for the interlocutor?
- How do LLM biases reflect social classification schemas rather than random errors?
- Is the distinction between pretense and realization meaningful for LLMs?
- What unique perspective do designers bring to LLM adaptation that engineers might miss?
- What makes human-LLM exchange closer to oracle-consultation than dialogue?
- Can the intentional stance meaningfully apply to entities with no stable self?
- Can LLM therapists develop character knowledge to decide when advice-giving fits?
- Why do LLM stories over-explain themes and favor single-track plots?
- What happens when humans animate LLM outputs as communicative events?
- Why does personal authenticity matter more for human persuasion than LLM?
- Why does weakening communication fail but weakening belief succeeds?
- Can LLMs serve as reliable intellectual opponents in serious debate or argument?
- How does this differ from using LLMs as the policy itself?
- Do psychological test methods reveal LLM associations that direct questions hide?
- What distinguishes actual social disagreement from distributional uncertainty in LLM outputs?
- What interaction design changes would help LLMs handle underspecified requests?
- How do prescriptive ethical constraints differ from descriptive ethical understanding in LLMs?
- How does role play differ from consciousness grounded in stable selfhood?
- What makes communication relational in ways belief is not?
- Why does optimism bias disappear when LLMs passively observe outcomes?
- What makes LLMs media rather than tools that deliver intelligence?
- Can LLMs themselves serve as research subjects for social science?
- What role does the biological substrate play in human relational identity?
- How do citizen assembly preferences reduce LLM political bias?