相关论文: GPT and Prejudice: A Sparse Approach to Understand…

As large language models (LLMs) have been used in many downstream tasks, the internal stereotypical representation may affect the fairness of the outputs. In this work, we introduce human knowledge into natural language interventions and…

We investigate whether Large Language Models (LLMs) exhibit human-like cognitive patterns under four established frameworks from psychology: Thematic Apperception Test (TAT), Framing Bias, Moral Foundations Theory (MFT), and Cognitive…

Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal unaligned representations, leaving LLMs vulnerable to long-tail risks. More crucially, we posit…

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…

Large Language Models (LLMs) are increasingly integrated into software engineering (SE) tools for tasks that extend beyond code synthesis, including judgment under uncertainty and reasoning in ethically significant contexts. We present a…

Modern text classification methods heavily rely on contextual embeddings from large language models (LLMs). Compared to human-engineered features, these embeddings provide automatic and effective representations for classification model…

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are…

Sparse autoencoders (SAEs) are a mechanistic interpretability technique that have been used to provide insight into learned concepts within large protein language models. Here, we employ TopK and Ordered SAEs to investigate autoregressive…

The recent advances in large language models (LLMs) have revolutionized industries such as finance, marketing, and customer service by enabling sophisticated natural language processing tasks. However, the broad adoption of LLMs brings…

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based…

Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…

Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are…

Background Advancements in Large Language Models (LLMs) hold transformative potential in healthcare, however, recent work has raised concern about the tendency of these models to produce outputs that display racial or gender biases.…

Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavior steering. Yet, a fundamental question remains unanswered:…

This paper examines how Large Language Models (LLMs) reproduce societal norms, particularly heterocisnormativity, and how these norms translate into measurable biases in their text generations. We investigate whether explicit information…

This study seeks to uncover evidence of a latent structure in evolved human culture as it is refracted through contemporary large language models (LLMs). Drawing on parallel responses from six leading generative models to a prompt which…

Masked Language Models (MLMs) pre-trained by predicting masked tokens on large corpora have been used successfully in natural language processing tasks for a variety of languages. Unfortunately, it was reported that MLMs also learn…

Implicit gender bias in Large Language Models (LLMs) is a well-documented problem, and implications of gender introduced into automatic translations can perpetuate real-world biases. However, some LLMs use heuristics or post-processing to…

To recognize and mitigate harms from large language models (LLMs), we need to understand the prevalence and nuances of stereotypes in LLM outputs. Toward this end, we present Marked Personas, a prompt-based method to measure stereotypes in…