相关论文: Value-Action Alignment in Large Language Models un…
Humans shift between different personas depending on social context. Large Language Models (LLMs) demonstrate a similar flexibility in adopting different personas and behaviors. Existing approaches, however, typically adapt such behavior…
The deployment of Large Language Models (LLMs) in embodied agents creates an urgent need to measure their privacy awareness in the physical world. Existing evaluation methods, however, are confined to natural language based scenarios. To…
Automatic Speech Recognition (ASR) plays a crucial role in human-machine interaction and serves as an interface for a wide range of applications. Traditionally, ASR performance has been evaluated using Word Error Rate (WER), a metric that…
Large Language Model (LLM) personas with explicit specifications of attributes, background, and behavioural tendencies are increasingly used to simulate human conversations for tasks such as user modeling, social reasoning, and behavioural…
As Large Language Models (LLMs) become widely used to model and simulate human behavior, understanding their biases becomes critical. We developed an experimental framework using Big Five personality surveys and uncovered a previously…
The emergence of large language models (LLMs) has opened up exciting possibilities for simulating human behavior and cognitive processes, with potential applications in various domains, including marketing research and consumer behavior…
The standard way to study Large Language Models (LLMs) with benchmarks or psychology questionnaires is to provide many different queries from similar minimal contexts (e.g. multiple choice questions). However, due to LLMs' highly…
Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often isolate model behavior from the broader system context. This work introduces a goal-driven…
The recent advances in large language models (LLMs) have significantly expanded their applications across various fields such as language generation, summarization, and complex question answering. However, their application to privacy…
Altruism is fundamental to human societies, fostering cooperation and social cohesion. Recent studies suggest that large language models (LLMs) can display human-like prosocial behavior, but the internal computations that produce such…
Large language models (LLMs) increasingly serve as human-like decision-making agents in social science and applied settings. These LLM-agents are typically assigned human-like characters and placed in real-life contexts. However, how these…
As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…
Recent studies evaluate the value orientation of large language models (LLMs) using adapted social surveys, typically by prompting models with survey questions and comparing their responses to average human responses. This paper identifies…
Large Language Models (LLMs) are widely used in sensitive domains, including healthcare, finance, and legal services, raising concerns about potential private information leaks during inference. Privacy extraction attacks, such as…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks. However, these models often infer and reveal sensitive biometric attributes such as race, gender, age, body weight, and eye color;…
Large Language Models (LLMs) not only have solved complex reasoning problems but also exhibit remarkable performance in tasks that require subjective decision making. Existing studies suggest that LLM generations can be subjectively…
Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during…
Aligning Large Language Models (LLMs) with human values has attracted increasing attention since it provides clarity, transparency, and the ability to adapt to evolving scenarios. In this paper, we introduce a Controlled Value Vector…
Large language models (LLMs) have achieved impressive performance, leading to their widespread adoption as decision-support tools in resource-constrained contexts like hiring and admissions. There is, however, scientific consensus that AI…
As large language models (LLMs) expose systemic security challenges in high risk applications, including privacy leaks, bias amplification, and malicious abuse, there is an urgent need for a dynamic risk assessment and collaborative defence…