paper-with-me

홈 › Papers

Interpolative Decoding: Exploring the Spectrum of Personality Traits in LLMs

2025-12-23 · Eric Yeh, John Cadigan, Ran Chen, Dick Crouch, Melinda Gervasio, Dayne Freitag arxiv

Recent research has explored using very large language models (LLMs) as proxies for humans in tasks such as simulation, surveys, and studies. While LLMs do not possess a human psychology, they often can emulate human behaviors with sufficiently high fidelity to drive simulations to test human behavioral hypotheses, exhibiting more nuance and range than the rule-based agents often employed in behavioral economics. One key area of interest is the effect of personality on decision making, but the requirement that a prompt must be created for every tested personality profile introduces experimental overhead and degrades replicability. To address this issue, we leverage interpolative decoding, representing each dimension of personality as a pair of opposed prompts and employing an interpolation parameter to simulate behavior along the dimension. We show that interpolative decoding reliably modulates scores along each of the Big Five dimensions. We then show how interpolative decoding causes LLMs to mimic human decision-making behavior in economic games, replicating results from human psychological research. Finally, we present preliminary results of our efforts to ``twin'' individual human players in a collaborative game through systematic search for points in interpolation space that cause the system to replicate actions taken by the human subject.

📄 PDF Abstract BibTeX arXiv:2512.19937

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Exploring the Potential of Large Language Models to Simulate Personality

2025-02-12 · Maria Molchanova, Anna Mikhailova, Anna Korzanova, Lidiia Ostyakova 외

With the advancement of large language models (LLMs), the focus in Conversational AI has shifted from merely generating coherent and relevant responses to tackling more complex challenges, such as personalizing dialogue …

Tailoring Personality Traits in Large Language Models via Unsupervisedly-Built Personalized Lexicons

2023-10-25 · Tianlong Li, Shihan Dou, Changze Lv, Wenhao Liu 외

Personality plays a pivotal role in shaping human expression patterns, thus regulating the personality of large language models (LLMs) holds significant potential in enhancing the user experience of LLMs. Previous method…

Giving AI Personalities Leads to More Human-Like Reasoning

2025-02-19 · Animesh Nighojkar, Bekhzodbek Moydinboyev, My Duong, John Licato

In computational cognitive modeling, capturing the full spectrum of human judgment and decision-making processes, beyond just optimal behaviors, is a significant challenge. This study explores whether Large Language Mode…

Natural Language Inference

Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models

2025-04-09 · Xiaoyan Zhao, Yang Deng, Wenjie Wang, Hongzhan Lin 외

Conversational Recommender Systems (CRSs) engage users in multi-turn interactions to deliver personalized recommendations. The emergence of large language models (LLMs) further enhances these systems by enabling more nat…

Conversational RecommendationRecommendation SystemsUser Simulation

What makes your model a low-empathy or warmth person: Exploring the Origins of Personality in LLMs

2024-10-07 · Shu Yang, Shenzhe Zhu, Ruoxuan Bao, Liang Liu 외

Large language models (LLMs) have demonstrated remarkable capabilities in generating human-like text and exhibiting personality traits similar to those in humans. However, the mechanisms by which LLMs encode and express …