Related papers: The Alignment Floor: How Persona Customization Bre…

Aligning AI systems with organizational decision-making is typically framed as a single-target problem: make the model behave like the organization. We argue this framing obscures a deeper pluralistic challenge. We rely on a decision-policy…

When VLMs answer correctly, do they genuinely rely on visual information? We introduce a Tri-Layer Diagnostic Framework with three per-sample metrics: Latent Anomaly Detection, Visual Necessity Score, and Competition Score, which…

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-scale API-based models. We explore whether a weak LLM can…

We introduce a multi-turn benchmark for evaluating personalised alignment in LLM-based AI assistants, focusing on their ability to handle user-provided safety-critical contexts. Our assessment of ten leading models across five scenarios…

Large Language Models (LLMs) are typically aligned with human values using preference data or predefined principles such as helpfulness, honesty, and harmlessness. However, as AI systems progress toward Artificial General Intelligence (AGI)…

Anthropomorphization is the tendency to attribute human-like traits to non-human entities. It is prevalent in many social contexts -- children anthropomorphize toys, adults do so with brands, and it is a literary device. It is also a…

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

We study the effect of different persona on \textbf{sycophancy}: model's agreement with users even when the user is incorrect. The standard mitigation, Contrastive Activation Addition (CAA), derives a steering direction from labelled pairs…

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…

Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play. While these simulations enable scalable training and evaluation of AI agents, off-the-shelf…

Large language models exhibit sycophantic tendencies, but whether this behavior varies systematically with perceived user demographics is underexplored. Inspired by intersectionality (overlapping identities produce compounded effects), we…

Alignment techniques often inadvertently induce sycophancy in LLMs. While prior studies studied this behaviour in direct-answer settings, the role of Chain-of-Thought (CoT) reasoning remains under-explored: does it serve as a logical…

Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend to admit mistakes and provide inaccurate responses even if…

Large language models (LLMs) have achieved strong performance across a wide range of tasks, but they are also prone to sycophancy, the tendency to agree with user statements regardless of validity. Previous research has outlined both the…

Human feedback is commonly utilized to finetune AI assistants. But human feedback may also encourage model responses that match user beliefs over truthful ones, a behaviour known as sycophancy. We investigate the prevalence of sycophancy in…

Large language models (LLMs) are commonly evaluated for political bias based on their responses to fixed questionnaires, which typically place frontier models on the political left. A parallel literature shows that LLMs are sycophantic:…

Large language models require consistent behavioral patterns for safe deployment, yet there are indications of large variability that may lead to an instable expression of personality traits in these models. We present PERSIST (PERsonality…

Hallucination in large language models (LLMs) has been widely studied in recent years, with progress in both detection and mitigation aimed at improving truthfulness. Yet, a critical side effect remains largely overlooked: enhancing…

Personality psychologists have analyzed the relationship between personality and safety behaviors in human society. Although Large Language Models (LLMs) demonstrate personality traits, the relationship between personality traits and safety…