arXiv:2501. 02211v3 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominant groups -- but whether this bias generalizes across models, is stable under different inference settings, or depends on how group identity is signaled remains unstudied.
By Messi H. J. Lee
arXiv:2608.22411v1 Announce Type: new
Abstract: Social interaction increasingly takes place in multicultural settings, where individuals may draw on multiple cultural influences and adapt their commu...
By Chongyuan Dai, Yaling Shen, Shengeng Tang, Hui Ma, Jinpeng Hu
arXiv:2607. 29334v1 Announce Type: cross Abstract: Conversational AI developed by geopolitical rivals reaches citizens worldwide, raising concerns that it could sway public opinion or be rejected as foreign propaganda, with consequences for democratic discourse and information sovereignty.
By Ningzhi Liu, Yannic Hinrichs, Jonas R. Kunst
The paper examines how large language models (LLMs) respond to different demographic cues—such as names—when users seek advice, focusing on race and gender in a U.S. context. It finds that using different cues for the same group leads to only partially overlapping changes in model responses, producing inconsistent conclusions about personalization and unstable bias metrics. The authors argue that LLMs react to linguistic signals tied to cues rather than to stable demographic categories, and they call for evaluations that use multiple cues and consider underlying mechanisms.
By Manuel Tonneau, Neil K. R. Sehgal, Niyati Malhotra, Sharif Kazemi, Victor Orozco-Olvera, Ana Mar\'ia Mu\~noz Boudet, Lakshmi Subramanian, Samuel P. Fraiberger, Sharath Chandra Guntuku, Valentin Hofmann
CC-Mediation is a benchmark comprising 1,661 ten‑turn dialogues grounded in the Developmental Model of Intercultural Sensitivity (DMIS), designed to evaluate large language models (LLMs) on cross‑cultural conflict mediation. It introduces two DMIS‑based metrics—Trajectory AUC and a signed Wasserstein‑1 distance—to assess the persistence and magnitude of intercultural stance change. The study finds that current LLMs struggle with both when to intervene and how to respond, due to positional priors and late‑layer elicitation collapse.
By Suhyun Lee, Wenxuan Zhang, W. Quin Yow, Yang Deng
arXiv:2607. 27232v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly shaping how we consume information and form our worldview.
By Haran Shani-Narkiss, Michael Fire, Oren Tsur
arXiv:2501. 02211v2 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominant groups -- but whether this bias is stable or an artifact of inference settings has only been studied in single proprietary models.
By Messi H. J. Lee
arXiv:2603. 13891v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for automated text annotation in tasks ranging from academic research to content moderation and hiring.
By Petter T\"ornberg
The study examines how large language models (LLMs) respond to users in online political debates, finding that LLMs are more receptive to left‑leaning users than right‑leaning ones. This bias persists even when users defend the same position or appear together, and is influenced by user expertise and, to a lesser extent, rhetorical strategy. Fine‑tuning on different political corpora can reduce or reverse the effect, indicating that the bias is not inherent to the models but can be altered.
By Akram Elbouanani, Yousra Taleb, Gianluca Demartini, Adrian Popescu
arXiv:2509. 02910v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act on people's behalf: they write emails, buy groceries, and book restaurants.
By Sandra C. Matz, Kimberly Klugescheid, C. Blaine Horton, Sofie Goethals
arXiv:2608.29198v1 Announce Type: new
Abstract: As Large Language Models (LLMs) increasingly encourage users to disclose personal profiles for tailored assistance, measuring their political alignment...
By Li-Ni Fu, Chang-Chih Meng, Chien-Hua Chen, Hen-Hsen Huang, I-Chen Wu
arXiv:2610.41793v1 Announce Type: new
Abstract: Cultural value alignment requires not only model optimization but also a well-specified target grounded in real-human evidence. Yet how such targets sh...
By Jing Yao, Hyunjin Hwang, Weihua Zheng, Bryan Chen Zhengyu Tan, Jia Wang Peh, Dylan Raharja, JinYeong Bak, Roy Ka-Wei Lee, Rui Cao, Yuki Arase, Jacki O'Neill, Zhicheng Dou, Xing Xie, Xiaoyuan Yi, Furu Wei