中文
相关论文

相关论文: Misalignment of LLM-Generated Personas with Human …

200 篇论文

Personalized dialogue systems have advanced considerably with the integration of user-specific personas into large language models (LLMs). However, while LLMs can effectively generate personalized responses, the influence of persona…

计算与语言 · 计算机科学 2025-06-03 Yonghyun Jun , Hwanhee Lee

Humans constantly generate a diverse range of tasks guided by internal motivations. While generative agents powered by large language models (LLMs) aim to simulate this complex behavior, it remains uncertain whether they operate on similar…

人工智能 · 计算机科学 2026-01-29 Yi-Long Lu , Jiajun Song , Chunhui Zhang , Wei Wang

Large Language Models (LLMs) are now increasingly widely used to simulate personas in virtual environments, leveraging their instruction-following capability. However, we discovered that even state-of-the-art LLMs cannot simulate personas…

计算与语言 · 计算机科学 2026-03-17 Sai Adith Senthil Kumar , Hao Yan , Saipavan Perepa , Murong Yue , Ziyu Yao

As Large Language Models (LLMs) become widely used to model and simulate human behavior, understanding their biases becomes critical. We developed an experimental framework using Big Five personality surveys and uncovered a previously…

We conduct a quantitative analysis contrasting human-written English news text with comparable large language model (LLM) output from six different LLMs that cover three different families and four sizes in total. Our analysis spans several…

计算与语言 · 计算机科学 2024-09-04 Alberto Muñoz-Ortiz , Carlos Gómez-Rodríguez , David Vilares

Large Language Models (LLMs) trained on extensive textual corpora have emerged as leading solutions for a broad array of Natural Language Processing (NLP) tasks. Despite their notable performance, these models are prone to certain…

计算与语言 · 计算机科学 2023-07-25 Yufei Wang , Wanjun Zhong , Liangyou Li , Fei Mi , Xingshan Zeng , Wenyong Huang , Lifeng Shang , Xin Jiang , Qun Liu

Large language models (LLMs) have brought breakthroughs in tasks including translation, summarization, information retrieval, and language generation, gaining growing interest in the CHI community. Meanwhile, the literature shows…

人机交互 · 计算机科学 2024-03-05 Lu Wang , Max Song , Rezvaneh Rezapour , Bum Chul Kwon , Jina Huh-Yoo

Large Language Models are being used in conversational agents that simulate human conversations and generate social studies data. While concerns about the models' biases have been raised and discussed in the literature, much about the data…

计算机与社会 · 计算机科学 2025-10-24 Guido Ivetta , Laura Moradbakhti , Rafael A. Calvo

Large Language Models (LLMs) have demonstrated the ability to adopt a personality and behave in a human-like manner. There is a large body of research that investigates the behavioural impacts of personality in less obvious areas such as…

统计金融 · 定量金融 2024-11-12 Harris Borman , Anna Leontjeva , Luiz Pizzato , Max Kun Jiang , Dan Jermyn

Aligning large language models (LLMs) typically aim to reflect general human values and behaviors, but they often fail to capture the unique characteristics and preferences of individual users. To address this gap, we introduce the concept…

计算与语言 · 计算机科学 2025-03-11 Minjun Zhu , Yixuan Weng , Linyi Yang , Yue Zhang

This paper delves into the dynamic landscape of artificial intelligence, specifically focusing on the burgeoning prominence of large language models (LLMs). We underscore the pivotal role of Reinforcement Learning from Human Feedback (RLHF)…

计算机与社会 · 计算机科学 2024-03-18 Dana Alsagheer , Rabimba Karanjai , Nour Diallo , Weidong Shi , Yang Lu , Suha Beydoun , Qiaoning Zhang

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 Models (LLMs) can…

人工智能 · 计算机科学 2025-02-24 Animesh Nighojkar , Bekhzodbek Moydinboyev , My Duong , John Licato

Large Language Models (LLMs) offer promising avenues for methodological and applied innovations in survey research by using synthetic respondents to emulate human answers and behaviour, potentially mitigating measurement and representation…

计算与语言 · 计算机科学 2025-09-22 Bastián González-Bustamante , Nando Verelst , Carla Cisternas

As Large Language Models (LLMs) continue to gain popularity due to their human-like traits and the intimacy they offer to users, their societal impact inevitably expands. This leads to the rising necessity for comprehensive studies to fully…

人工智能 · 计算机科学 2025-01-07 Bojana Bodroza , Bojana M. Dinic , Ljubisa Bojic

As the deployment of large language models (LLMs) expands, there is an increasing demand for personalized LLMs. One method to personalize and guide the outputs of these models is by assigning a persona -- a role that describes the expected…

计算与语言 · 计算机科学 2024-09-19 Mahammed Kamruzzaman , Hieu Nguyen , Nazmul Hassan , Gene Louis Kim

Large language models (LLMs) are increasingly used to simulate human decision-making, but their intrinsic biases often diverge from real human behavior--limiting their ability to reflect population-level diversity. We address this challenge…

计算机科学与博弈论 · 计算机科学 2025-08-27 Ayato Kitadai , Yusuke Fukasawa , Nariaki Nishino

The burgeoning capabilities of large language models (LLMs) have underscored the need for alignment to ensure these models act in accordance with human values and intentions. Existing alignment frameworks present constraints either in the…

计算与语言 · 计算机科学 2025-04-28 Leitian Tao , Yixuan Li

When Artificial Intelligence (AI) is used to replace consumers (e.g., synthetic data), it is often assumed that AI emulates established consumers, and more generally human behaviors. Ten experiments with Large Language Models (LLMs)…

Evaluating AI systems that interact with humans requires understanding their behavior across diverse user populations, but collecting representative human data is often expensive or infeasible, particularly for novel technologies or…

Large language models (LLMs) are increasingly capable of simulating human behavior, offering cost-effective ways to estimate user responses to various surveys and polls. However, the questions in these surveys usually reflect socially…

计算与语言 · 计算机科学 2025-09-03 Minwoo Kang , Suhong Moon , Seung Hyeong Lee , Ayush Raj , Joseph Suh , David M. Chan , John Canny