相关论文: Intersectional Sycophancy: How Perceived User Demo…

We introduce the identity labeling problem - given an individual in a social situation, can we predict what identity(ies) they will be labeled with by someone else? This problem remains a theoretical gap and methodological challenge,…

ChatGPT is notorious for its intransparent behavior. This paper tries to shed light on this, providing an in-depth analysis of the dark personality traits and conspiracy beliefs of GPT-3.5 and GPT-4. Different psychological tests and…

Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and biases, particularly across intersectional demographic attributes. In this paper, we systematically evaluate…

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

Sycophancy in Vision-Language Models (VLMs) refers to their tendency to align with user opinions, often at the expense of moral or factual accuracy. While prior studies have explored sycophantic behavior in general contexts, its impact on…

Silicon samples are increasingly used as a low-cost substitute for human panels and have been shown to reproduce aggregate human opinion with high fidelity. We show that, in the alignment-relevant domain of philosophy, silicon samples…

Self-consistency has emerged as a popular technique for improving large language model accuracy on reasoning tasks. The approach is straightforward: generate multiple reasoning paths and select the most common answer through majority…

Work on personality detection has tended to incorporate psychological features from different personality models, such as BigFive and MBTI. There are more than 900 psychological features, each of which is helpful for personality detection.…

While personalized recommendations are often desired by users, it can be difficult in practice to distinguish cases of bias from cases of personalization: we find that models generate racially stereotypical recommendations regardless of…

The lexical hypothesis posits that personality traits are encoded in language and is foundational to models like the Big Five. We created a bottom-up personality model from a classic adjective list using machine learning and compared its…

Benchmarks underpin how progress in large language models (LLMs) is measured and trusted. Yet our analyses reveal that apparent convergence in benchmark accuracy can conceal deep epistemic divergence. Using two major reasoning benchmarks -…

Large language models (LLMs) are increasingly used as autonomous agents in strategic and social interactions. Although recent studies suggest that assigning personality traits to LLMs can influence their behavior, how personality steering…

If large language models like GPT-3 preferably produce a particular point of view, they may influence people's opinions on an unknown scale. This study investigates whether a language-model-powered writing assistant that generates some…

Large Language Models have garnered significant attention for their capabilities in multilingual natural language processing, while studies on risks associated with cross biases are limited to immediate context preferences. Cross-language…

As the application of Large Language Models (LLMs) spreads across various industries, there are increasing concerns about the potential for their misuse, especially in sensitive areas such as political discourse. Deliberately aligning LLMs…

Recent studies have shown that prompting can enable large language models (LLMs) to simulate specific personality traits and produce behaviors that align with those traits. However, there is limited understanding of how these simulated…

Large language models (LLMs) have been shown to propagate and amplify harmful stereotypes, particularly those that disproportionately affect marginalised communities. To understand the effect of these stereotypes more comprehensively, we…

Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Therefore, it is of great importance to evaluate their emerging abilities. In this study, we show that LLMs,…

Adaptive chatbots that mimic a user's linguistic style can build rapport and engagement, yet unconstrained mimicry risks an agent that feels unstable or sycophantic. We present a computational evaluation framework that makes the core design…

Language model (LM) assistants are increasingly used in applications such as brainstorming and research. Improvements in memory and context size have allowed these models to become more autonomous, which has also resulted in more text…