Modeling Pathology-Like Behavioral Patterns in Language Models Through Behavioral Fine-Tuning

TL;DR

This paper demonstrates that fine-tuning large language models on synthetic behavioral datasets can induce stable, systematic behavioral patterns that influence their language generation and interpretative tendencies.

Contribution

The study introduces a behavioral induction framework for LLMs, showing how structured fine-tuning can produce specific, dissociable behavioral biases in language models.

Findings

Fine-tuned models show increased negative and threat-related language.

Behavioral biases generalize across contexts and are detectable in multiple evaluation methods.

Different behavioral patterns lead to distinct response tendencies.

Abstract

Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using synthetic datasets inspired by maladaptive behavioral patterns, including depression and paranoia, we train transformer-based language models to consistently select specific classes of actions across diverse contexts. We then test whether this behavioral optimization produces systematic changes in generative distributions. Across two architectures, fine-tuned models show stable, context-general shifts in next-token probability distributions, including increased probability assigned to negative and threat-related interpretations in open-ended language tasks. These effects generalize beyond training contexts and are detectable in qualitative completions, psychometric-style evaluations, and quantitative distributional metrics such as Jensen-Shannon divergence. Induced behavioral profiles also show partial specificity. Models optimized for different behavioral patterns exhibit dissociable response tendencies across evaluation probes, suggesting that structured behavioral training produces differentiated policy-level biases rather than generic distributional skew. We interpret these findings as evidence that consistent behavioral optimization in LLMs can generate stable behavioral and distributional patterns consistent with altered latent priors, linking action selection and language generation. More broadly, the results support a view of LLMs as policy-based systems in which behavioral constraints shape emergent representational structure, highlighting their potential as controlled testbeds for studying the relationship between behavior, interpretation, and generative language in computational models of cognition.