相关论文: Persona Vectors: Monitoring and Controlling Charac…

Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic…

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…

Driven by the demand for personalized AI systems, there is growing interest in aligning the behavior of large language models (LLMs) with human traits such as personality. Previous attempts to induce personality in LLMs have shown promising…

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…

It is becoming increasingly necessary to have monitors check for harmful behaviors during language model interactions, but text-only monitoring has not been sufficient. This is because models sometimes exhibit strategic deception and…

Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning, failing to capture the dynamic and compositional nature of human traits. We introduce PERSONA, a training-free framework…

One way to personalize and steer generations from large language models (LLM) is to assign a persona: a role that describes how the user expects the LLM to behave (e.g., a helpful assistant, a teacher, a woman). This paper investigates how…

The influence of personas on Large Language Models (LLMs) has been widely studied, yet their direct impact on performance remains uncertain. This work explores a novel approach to guiding LLM behaviour through role vectors, an alternative…

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…

With the emergence of large language models (LLMs) as a powerful class of generative artificial intelligence (AI), their use in tutoring has become increasingly prominent. Prior works on LLM-based tutoring typically learn a single tutor…

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…

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

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…

As language models continue to scale in size and capability, they display an array of emerging behaviors, both beneficial and concerning. This heightens the need to control model behaviors. We hope to be able to control the personality…

Recent work shows that large language models (LLMs) encode behavioural traits ("personas") as linear directions in activation space, often called "persona vectors". Prior work has used such directions as static handles for behavioural…

Psychology research has long explored aspects of human personality such as extroversion, agreeableness and emotional stability. Categorizations like the `Big Five' personality traits are commonly used to assess and diagnose personality…

Activation-based steering can personalize large language models at inference time, but its effects in educational settings remain unclear. We study persona vectors for seven character traits in short-answer generation and automated scoring…

Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underexplored. We identify two alignment-induced biases in existing methods: a positive moral bias,…

Personality traits have long been studied as predictors of human behavior. Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems, with advanced LLMs displaying consistent behavioral…

Large language models (LLMs) have shown remarkable promise in simulating human language and behavior. This study investigates how integrating persona variables-demographic, social, and behavioral factors-impacts LLMs' ability to simulate…