analiza aiqbench
This research introduces PACIFIC, a framework that leverages Big-Five personality traits to enhance the reliability of personalized Large Language Model responses by filtering noisy user preference data. By employing a persona-aware contrastive retriever, the study demonstrates that aligning LLMs with stable psychological profiles significantly improves answer accuracy without requiring explicit trait annotations during inference. The work identifies information retrieval as the primary bottleneck in current personalization efforts rather than the models' inherent reasoning capabilities.
PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? Personality-Driven Preference Alignment in LLMs
arXiv:2602.07181v4 Announce Type: replace Abstract: User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet reliably leveraging preference signals remains under-explored. In practice, preferences can be noisy, incomplete, or even misleading, which can degrade answer quality when applied naively. Motivated by the observation that stable personality traits shape everyday preferences, we introduce PACIFIC (Preference Alignment for Choices Inference via Five-factor Identity Characterization), a personality-driven preference alignment framework that uses Big-Five (OCEAN) traits as a principled "latent" signal for organizing and reasoning over user preference history. To systematically evaluate this framework, we construct a psychometrics-based dataset containing 1,200 preference-query pairs spanning diverse domains (e.g., travel, movies, and education), with comprehensive coverage of high and low Big-Five trait directions. Extensive experiments show that trait-aligned preferences substantially improve personalized QA: given clean, trait-aligned context, LLMs reach near-ceiling accuracy (up to 99%), confirming that reasoning capability is not the bottleneck. The challenge is that real histories are mixed-trait and unlabeled. We show the true bottleneck is retrieval: a persona-aware contrastive retriever (PiRAG) raises label-free accuracy from 30% to 43% over standard semantic retrieval, without any trait annotations at inference.
Title:PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? Personality-Driven Preference Alignment in LLMs
Abstract:User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet reliably leveraging preference signals remains under-explored. In practice, preferences can be noisy, incomplete, or even misleading, which can degrade answer quality when applied naively. Motivated by the observation that stable personality traits shape everyday preferences, we introduce PACIFIC (Preference Alignment for Choices Inference via Five-factor Identity Characterization), a personality-driven preference alignment framework that uses Big-Five (OCEAN) traits as a principled "latent" signal for organizing and reasoning over user preference history. To systematically evaluate this framework, we construct a psychometrics-based dataset containing 1,200 preference-query pairs spanning diverse domains (e.g., travel, movies, and education), with comprehensive coverage of high and low Big-Five trait directions. Extensive experiments show that trait-aligned preferences substantially improve personalized QA: given clean, trait-aligned context, LLMs reach near-ceiling accuracy (up to 99%), confirming that reasoning capability is not the bottleneck. The challenge is that real histories are mixed-trait and unlabeled. We show the true bottleneck is retrieval: a persona-aware contrastive retriever (PiRAG) raises label-free accuracy from 30% to 43% over standard semantic retrieval, without any trait annotations at inference.
Computation and Language (cs.CL)
arXiv:2602.07181 [cs.CL]
(or arXiv:2602.07181v4 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2602.07181 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 291 cuvinte
Subiecte conexe
Emotional Labor Strategy Preferences in LLM Personas
arXiv · 2 sept. 2026
Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble
LessWrong · 21 sept. 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits
arXiv · 17 sept. 2026