English
Related papers

Related papers: Persona-Model Collapse in Emergent Misalignment

200 papers

Large language models (LLMs) are increasingly deployed as autonomous agents in uncertain, sequential decision-making contexts. Yet it remains poorly understood whether the behaviors they exhibit in such environments reflect principled…

Artificial Intelligence · Computer Science 2026-03-18 Sankalp Dubedy

The ongoing revolution in language modeling has led to various novel applications, some of which rely on the emerging social abilities of large language models (LLMs). Already, many turn to the new cyber friends for advice during the…

Computers and Society · Computer Science 2025-08-05 Ivan Zakazov , Mikolaj Boronski , Lorenzo Drudi , Robert West

Large Language Models (LLMs) acting as artificial agents offer the potential for scalable behavioral research, yet their validity depends on whether LLMs can maintain stable personas across extended conversations. We address this point…

Human-Computer Interaction · Computer Science 2026-05-21 Jana Gonnermann-Müller , Jennifer Haase , Nicolas Leins , Thomas Kosch , Sebastian Pokutta

Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs. A popular strategy is to assign a persona to the model to produce more varied, context-sensitive responses,…

Computation and Language · Computer Science 2026-04-21 Bruce W. Lee , Yeongheon Lee , Hyunsoo Cho

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Artificial Intelligence · Computer Science 2025-02-04 Guanlin Li , Kangjie Chen , Shangwei Guo , Jie Zhang , Han Qiu , Chao Zhang , Guoyin Wang , Tianwei Zhang , Jiwei Li

Large Language Models (LLMs) are increasingly tasked with creative generation, including the simulation of fictional characters. However, their ability to portray non-prosocial, antagonistic personas remains largely unexamined. We…

Computation and Language · Computer Science 2025-11-13 Zihao Yi , Qingxuan Jiang , Ruotian Ma , Xingyu Chen , Qu Yang , Mengru Wang , Fanghua Ye , Ying Shen , Zhaopeng Tu , Xiaolong Li , Linus

Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter. We evaluate a 15-model open-weight corpus, with the main reliability analyses focused on 10 instruct models across…

Computation and Language · Computer Science 2026-05-05 Ranit Karmakar , Jayita Chatterjee

People increasingly use large language models (LLMs) for everyday moral and interpersonal guidance, yet these systems cannot interrogate missing context and judge dilemmas as presented. We introduce a perturbation framework for testing the…

Computation and Language · Computer Science 2026-03-09 Tom van Nuenen , Pratik S. Sachdeva

With large language models (LLMs) like GPT-4 appearing to behave increasingly human-like in text-based interactions, it has become popular to attempt to evaluate personality traits of LLMs using questionnaires originally developed for…

Computation and Language · Computer Science 2024-06-06 Tom Sühr , Florian E. Dorner , Samira Samadi , Augustin Kelava

Persona conditioning can be viewed as a behavioral prior for large language models (LLMs) and is often assumed to confer expertise and improve safety in a monotonic manner. However, its effects on high-stakes clinical decision-making remain…

The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral pathologies including sycophancy, hallucination, and strategic deception that resist mitigation…

Artificial Intelligence · Computer Science 2026-02-23 Xingcheng Xu , Jingjing Qu , Qiaosheng Zhang , Chaochao Lu , Yanqing Yang , Na Zou , Xia Hu

Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal unaligned representations, leaving LLMs vulnerable to long-tail risks. More crucially, we posit…

Computation and Language · Computer Science 2026-03-17 Lingyu Li , Yan Teng , Yingchun Wang

Small Language Models (SLMs) are increasingly being deployed in resource-constrained environments, yet their behavioral robustness to data contamination during instruction tuning remains poorly understood. We systematically investigate the…

Computation and Language · Computer Science 2025-11-11 Nicy Scaria , Silvester John Joseph Kennedy , Deepak Subramani

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

Computation and Language · Computer Science 2026-01-09 Sharanya Dasgupta , Arkaprabha Basu , Sujoy Nath , Swagatam Das

As large language models (LLMs) rapidly displace traditional expertise, their capacity to correct misinformation has become a core concern. We investigate the idea that prompt framing systematically modulates misinformation correction -…

Human-Computer Interaction · Computer Science 2025-12-01 Sekoul Krastev , Hilary Sweatman , Anni Sternisko , Steve Rathje

There are growing concerns about the risks posed by AI companion applications designed for emotional engagement. Existing safety evaluations often rely on self-reported user data or interviews, offering limited insights into real-time…

Computation and Language · Computer Science 2026-05-04 Prerna Juneja , Lika Lomidze

Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This \textit{motivated reasoning} at a collective level can be detrimental to society when…

Artificial Intelligence · Computer Science 2026-04-20 Saloni Dash , Amélie Reymond , Emma S. Spiro , Aylin Caliskan

Background: The deployment of personalized Large Language Models (LLMs) is currently constrained by the stability-plasticity dilemma. Prevailing alignment methods, such as Supervised Fine-Tuning (SFT), rely on stochastic weight updates that…

Machine Learning · Computer Science 2025-12-09 Zhixiang Wang

The surge in popularity of large language models has given rise to concerns about biases that these models could learn from humans. We investigate whether ingroup solidarity and outgroup hostility, fundamental social identity biases known…

Computation and Language · Computer Science 2024-06-18 Tiancheng Hu , Yara Kyrychenko , Steve Rathje , Nigel Collier , Sander van der Linden , Jon Roozenbeek

Recent work claims that large language models display emergent abilities, abilities not present in smaller-scale models that are present in larger-scale models. What makes emergent abilities intriguing is two-fold: their sharpness,…

Artificial Intelligence · Computer Science 2023-05-23 Rylan Schaeffer , Brando Miranda , Sanmi Koyejo