How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Persona Ratings Across Multiple LLMs and Humans
A new paper evaluates whether large language models can reliably assess social attraction by comparing their ratings to human judgments across 12 persona profiles.
- The study tested 34 LLMs on their ability to rate social attraction using 12 persona profiles grounded in psychological constructs.
- LLM ratings were compared to human judgments to assess their accuracy and consistency in social evaluations.
- Results indicate variability in LLM performance, suggesting both promise and limitations in using AI for subjective social assessments.
- The research underscores the need for caution when deploying LLMs in roles requiring human-like social perception.
A recent study published on arXiv explores the capability of large language models (LLMs) to perform subjective social evaluations, specifically assessing social attraction. The research constructs 12 persona profiles using ten psychological and relational constructs, categorized into socially attractive, mixed, and unattractive tiers. In the first study, 34 LLMs rated these profiles across three repeated runs to gauge consistency. The results were then compared to human judgments in a third study to evaluate the models' alignment with human social perception. The findings highlight both the potential and limitations of LLMs in mirroring human social evaluations, raising questions about their reliability in subjective domains traditionally reserved for human assessment.
Highlights the challenges and opportunities in using LLMs for subjective tasks beyond factual outputs.
Provides insight into the capabilities and limitations of AI in social perception and psychology-related applications.
Raises questions about the role of AI in human-like social judgments.
- Social attraction
- The perceived desirability or appeal of a person in social contexts, often assessed through psychological constructs.
- Persona profiles
- Detailed descriptions of individuals constructed from psychological and relational traits for evaluation purposes.
North Carolina Central University made history as the first HBCU in the nation to launch a dedicated AI research center - ABC11 News
Artificial intelligence institute opens at N.C. Central University - WPTF
AI ResearchAI professors are negotiating the new realities of academic research
With a feel for physics, AI models simulate a wider range of real-world scenarios - news.mit.edu
Artificial Intelligence in Dermoscopy: Why Expert Oversight Still Matters - Medscape
OpenAI reportedly completed a $7 billion employee tender offer
OpenAI has reportedly finalized a $7 billion tender offer to allow employees to sell their shares.
Roundup of California’s 2026 technology bills - Reason Foundation
California is preparing a slate of 2026 technology bills, with a focus on AI governance, data privacy, and algorithmic accountability.
As AI-led attacks multiply, OpenAI launches a new cyber model
OpenAI introduces a new AI model designed for cybersecurity defense as AI-powered attacks escalate globally.
Newsom to California agencies: Better prepare for artificial intelligence attacks - Sacramento Bee
California Governor Gavin Newsom has directed state agencies to prepare for AI-powered cyberattacks, citing rising risks from advanced AI tools.
Five takeaways from Zuckerberg’s AI manifesto - The Detroit News
Meta CEO Mark Zuckerberg outlines five core principles for AI development in a new manifesto, emphasizing open-source collaboration and ethical deployment.
BusinessWith new open models, Meta pitches another reboot of its struggling AI strategy
Meta unveils new open-source AI models to regain ground against rivals, signaling a strategic pivot after falling behind in the AI race.