相关论文: Persona-Model Collapse in Emergent Misalignment

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…

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…

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…

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,…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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 -…

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…

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…

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…

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…

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,…