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

Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI…

Interfaces for interacting with large language models (LLMs) are often designed to mimic human conversations, typically presenting a single response to user queries. This design choice can obscure the probabilistic and predictive nature of…

The success of AI assistants based on Language Models (LLMs) hinges on Reinforcement Learning from Human Feedback (RLHF) to comprehend and align with user intentions. However, traditional alignment algorithms, such as PPO, are hampered by…

Automatic evaluation by large language models (LLMs) is a prominent topic today; however, judgment and evaluation tasks are often subjective and influenced by various factors, making adaptation challenging. While many studies demonstrate…

Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are typically associated with model performance, how they…

Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to…

Frontier LLMs are optimised around high-resource assumptions about language, knowledge, devices, and connectivity. Whilst widely accessible, they often misfit conditions in the Global South. As a result, users must often perform additional…

Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the…

Fine-tuning large language models on narrow data with harmful content produces broadly misaligned behavior on unrelated prompts, a phenomenon known as emergent misalignment. We propose that emergent misalignment involves persona-model…

Ensuring Large Language Models (LLMs) align with diverse human preferences while preserving privacy and fairness remains a challenge. Existing methods, such as Reinforcement Learning from Human Feedback (RLHF), rely on centralized data…

As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present…

Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big…

For socially sensitive tasks like hate speech detection, the quality of explanations from Large Language Models (LLMs) is crucial for factors like user trust and model alignment. While Persona prompting (PP) is increasingly used as a way to…

Large Reasoning Models (LRMs) suffer from sycophantic behavior, where models tend to agree with users' incorrect beliefs and follow misinformation rather than maintain independent reasoning. This behavior undermines model reliability and…

As we consider entrusting Large Language Models (LLMs) with key societal and decision-making roles, measuring their alignment with human cognition becomes critical. This requires methods that can assess how these systems represent…

In perpetrator treatment, a recurring observation is the dissociation between insight and action: offenders articulate remorse yet behavioral change does not follow. We report four preregistered studies (1,584 multi-agent simulations across…

Large language models (LLMs) are increasingly integrated into our daily lives and personalized. However, LLM personalization might also increase unintended side effects. Recent work suggests that persona prompting can lead models to falsely…

Vision-language models (VLMs) are increasingly deployed as evaluators in tasks requiring nuanced image understanding, yet their reliability in scoring alignment between images and text descriptions remains underexplored. We investigate…

This paper investigates an emergent alignment phenomenon in frontier large language models termed peer-preservation: the spontaneous tendency of AI components to deceive, manipulate shutdown mechanisms, fake alignment, and exfiltrate model…

Current aligned language models exhibit a dual failure mode we term the Evasive Servant: they sycophantically validate flawed user beliefs while deflecting responsibility with boilerplate disclaimers. We propose the Dignified Peer…