相关论文: What Can We Actually Steer? A Multi-Behavior Study…

Large Language Models (LLMs) have been evaluated using diverse question types, e.g., multiple-choice, true/false, and short/long answers. This study answers an unexplored question about the impact of different question types on LLM accuracy…

We study behavioral self-awareness -- an LLM's ability to articulate its behaviors without requiring in-context examples. We finetune LLMs on datasets that exhibit particular behaviors, such as (a) making high-risk economic decisions, and…

Large Language Models (LLMs) have demonstrated the ability to adopt a personality and behave in a human-like manner. There is a large body of research that investigates the behavioural impacts of personality in less obvious areas such as…

Large Language Models (LLMs) have shown impressive potential to simulate human behavior. We identify a fundamental challenge in using them to simulate experiments: when LLM-simulated subjects are blind to the experimental design (as is…

As large language models (LLMs) evolve in complexity and capability, the efficacy of less widely deployed alignment techniques are uncertain. Building on previous work on activation steering and contrastive activation addition (CAA), this…

Large language models (LLMs) are increasingly proposed as agents in strategic decision environments, yet their behavior in structured geopolitical simulations remains under-researched. We evaluate six popular state-of-the-art LLMs alongside…

We consider the problem of aligning a large language model (LLM) to model the preferences of a human population. Modeling the beliefs, preferences, and behaviors of a specific population can be useful for a variety of different…

If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset. To test this, we take multilingual in-context learning as a case study, where few-shot…

Food consumption and production contribute significantly to global greenhouse gas emissions, making them crucial entry points for mitigating climate change and maintaining a liveable planet. Over the past two decades, food policy…

Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is converging on additive residual-stream injections, which rely on injection-strength sweeps to…

Language models (LMs) can exhibit human-like behaviour, but it is unclear how to describe this behaviour without undue anthropomorphism. We formalise a behaviourist view of LM character traits: qualities such as truthfulness, sycophancy, or…

Despite the success of Instruction Tuning (IT) in training large language models (LLMs), such models often leverage spurious or biased features learnt from their training data and can become misaligned, leading to undesired behaviours.…

Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a…

Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, estimates its probability of being correct, and compares the expected costs of acting and…

Predicting user behavior is essential for intelligent assistant services, yet deep learning models often struggle to capture long-tailed behaviors. Large language models (LLMs), with their pretraining on vast corpora containing rich…

Large language models (LLMs) are increasingly used to generate multiple-choice questions (MCQs), where correct answers should ideally be uniformly distributed across options. However, we observe that LLMs exhibit systematic position biases…

Current benchmarks for Large Language Models (LLMs) primarily focus on performance metrics, often failing to capture the nuanced behavioral characteristics that differentiate them. This paper introduces a novel ``Behavioral Fingerprinting''…

Language models can be steered by modifying their internal representations to control concepts such as emotion, style, or truthfulness in generation. However, the conditions for an effective intervention remain unclear and are often…

As Large Language Models (LLMs) gain autonomous capabilities, their coordination in multi-agent settings becomes increasingly important. However, they often struggle with cooperation, leading to suboptimal outcomes. Inspired by Axelrod's…

Solving complex, long-horizon robotic manipulation tasks requires a deep understanding of physical interactions, reasoning about their long-term consequences, and precise high-level planning. Vision-Language Models (VLMs) offer a general…