analiza aiqbench
This research applies large language models to quantify depression narratives and demonstrates that perturbing these narrative structures causally influences mood and cognition through a shared latent computational state. The study supports the hypothesis that metareasoning constraints govern interactions between affect, narrative, and thought within this unified framework. By bridging formal AI modeling with psychological phenomena like emotional regulation, it offers new insights into how generative models can simulate human-like cognitive-affective loops.
Metareasoning constraints couple narratives, affect and cognition
arXiv:2502.09487v4 Announce Type: replace Abstract: Narratives and emotions shape thoughts, and thoughts shape our feelings and stories we tell. Why narrative, affective and cognitive states interact remains unclear. We examine whether this mutual relationship reflects constraints on metareasoning - deciding what to think about - imposed by a shared computational state. Combining self-report and quantification of depression narratives using large language models, Study 1 (n=704) shows narrative state structure closely reflects the factorial structure in formal affect assessments, and that perturbation of the narrative state has commensurate effects on affect via a latent computational state. Study 2 (n=553) uses exposure to structured narratives to test model predictions causally in vivo. Narrative exposure has consistent effect on narrative states, with consequences on momentary mood, cognition, and affect. Critically, effects are predicted by latent computational state engagement. This supports the hypothesis that metareasoning constraints determine interactions between narratives, cognition and affect via a shared computational state.
Abstract:Narratives and emotions shape thoughts, and thoughts shape our feelings and stories we tell. Why narrative, affective and cognitive states interact remains unclear. We examine whether this mutual relationship reflects constraints on metareasoning - deciding what to think about - imposed by a shared computational state. Combining self-report and quantification of depression narratives using large language models, Study 1 (n=704) shows narrative state structure closely reflects the factorial structure in formal affect assessments, and that perturbation of the narrative state has commensurate effects on affect via a latent computational state. Study 2 (n=553) uses exposure to structured narratives to test model predictions causally in vivo. Narrative exposure has consistent effect on narrative states, with consequences on momentary mood, cognition, and affect. Critically, effects are predicted by latent computational state engagement. This supports the hypothesis that metareasoning constraints determine interactions between narratives, cognition and affect via a shared computational state.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2502.09487 [cs.CL]
(or arXiv:2502.09487v4 [cs.CL] for this version)
Text integral sub licența deschisă a publicației · 167 cuvinte
Subiecte conexe
Dialogue with Eliezer Yudkowsky on Neural Networks
LessWrong · 2 oct. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026
Links #5: 2026/07
LessWrong · 31 iul. 2026
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
Latent Space · 9 sept. 2026