相关论文: Do Linear Probes Generalize Better in Persona Coor…

Large language models interact with users through a simulated 'Assistant' persona. While the Assistant is typically trained to be helpful, harmless, and honest, it sometimes deviates from these ideals. In this paper, we identify directions…

Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However,…

White-box monitors are a popular technique for detecting potentially harmful behaviours in language models. While they perform well in general, their effectiveness in detecting text-ambiguous behaviour is disputed. In this work, we find…

Using persona-conditioned LLMs as synthetic survey respondents has become a common practice in computational social science and agent-based simulations. Yet, it remains unclear whether multi-attribute persona prompting improves LLM…

AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned. We thus…

Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as…

How large language models internally represent high-level behaviors is a core interpretability question with direct relevance to AI safety: it determines what we can detect, audit, or intervene on. Recent work has shown that traits such as…

Large language models (LLMs) can be said to have preferences: they reliably pick certain tasks and outputs over others, and preferences shaped by post-training and system prompts appear to shape much of their behaviour. But models can also…

Dialogue systems in the form of chatbots and personal assistants are being increasingly integrated into people's lives. Modern dialogue systems may consider adopting anthropomorphic personas, mimicking societal demographic groups to appear…

Large Language Models (LLMs) have started to demonstrate the ability to persuade humans, yet our understanding of how this dynamic transpires is limited. Recent work has used linear probes, lightweight tools for analyzing model…

Large language models (LLMs) exhibit distinct and consistent personalities that greatly impact trust and engagement. While this means that personality frameworks would be highly valuable tools to characterize and control LLMs' behavior,…

Persona-assigned large language models (LLMs) are used in domains such as education, healthcare, and sociodemographic simulation. Yet, they are typically evaluated only in short, single-round settings that do not reflect real-world usage.…

Probes trained on model activations can detect undesirable behaviors like deception or biases that are difficult to identify from outputs alone. This makes them useful detectors to identify misbehavior. Furthermore, they are also valuable…

Linear probes can detect when language models produce outputs they "know" are wrong, a capability relevant to both deception and reward hacking. However, single-layer probes are fragile: the best layer varies across models and tasks, and…

Large language models can represent a variety of personas but typically default to a helpful Assistant identity cultivated during post-training. We investigate the structure of the space of model personas by extracting activation directions…

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

Personalization of LLMs by sociodemographic subgroup often improves user experience, but can also introduce or amplify biases and unfair outcomes across groups. Prior work has employed so-called personas, sociodemographic user attributes…

Persona prompting is widely used to steer large language models, yet its practical value remains unclear. Prior work often evaluates persona prompting using aggregate scores, making it difficult to determine whether expert-role prompting…

Developing effective world models is crucial for creating artificial agents that can reason about and navigate complex environments. In this paper, we investigate a deep supervision technique for encouraging the development of a world model…

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…