PsychoLex: Unveiling the Psychological Mind of Large Language Models

TL;DR

This paper introduces PsychoLex, a specialized suite of resources and models designed to improve large language models' performance in psychological tasks across Persian and English, advancing AI's role in psychological research.

Contribution

The paper presents PsychoLexQA, PsychoLexEval datasets, and PsychoLexLLaMA, a model optimized for psychological applications, marking a novel step in domain-specific LLM development.

Findings

PsychoLexLLaMA outperforms general-purpose models in psychological tasks.

The datasets enable rigorous evaluation of LLMs in complex psychological scenarios.

Tailored LLMs can significantly enhance AI's utility in psychological research.

Abstract

This paper explores the intersection of psychology and artificial intelligence through the development and evaluation of specialized Large Language Models (LLMs). We introduce PsychoLex, a suite of resources designed to enhance LLMs' proficiency in psychological tasks in both Persian and English. Key contributions include the PsychoLexQA dataset for instructional content and the PsychoLexEval dataset for rigorous evaluation of LLMs in complex psychological scenarios. Additionally, we present the PsychoLexLLaMA model, optimized specifically for psychological applications, demonstrating superior performance compared to general-purpose models. The findings underscore the potential of tailored LLMs for advancing psychological research and applications, while also highlighting areas for further refinement. This research offers a foundational step towards integrating LLMs into specialized psychological domains, with implications for future advancements in AI-driven psychological practice.