Related papers: Self-Debias: Self-correcting for Debiasing Large L…

As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their decision-making. While traditional probing methods have…

Learning to reason and carefully explain arguments is central to students' cognitive, mathematical, and computational thinking development. This is particularly challenging in problems under uncertainty and in Bayesian reasoning. With the…

Gender bias exists in natural language datasets which neural language models tend to learn, resulting in biased text generation. In this research, we propose a debiasing approach based on the loss function modification. We introduce a new…

Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their ability to use bidirectional context and adapt to a specific ASR…

Text-to-image (T2I) diffusion models have achieved widespread success due to their ability to generate high-resolution, photorealistic images. These models are trained on large-scale datasets, like LAION-5B, often scraped from the internet.…

The deployment of Large Language Models (LLMs) in diverse applications necessitates an assurance of safety without compromising the contextual integrity of the generated content. Traditional approaches, including safety-specific fine-tuning…

Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for…

With the rapid development of large language models (LLMs), they have significantly improved efficiency across a wide range of domains. However, recent studies have revealed that LLMs often exhibit gender bias, leading to serious social…

Prior interpretability research studying narrow distributions has preliminarily identified self-repair, a phenomena where if components in large language models are ablated, later components will change their behavior to compensate. Our…

As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial. Despite many efforts, an ongoing challenge is hidden bias: LLMs appear fair under…

Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

Large language models (LLMs) offer an inexpensive yet powerful way to annotate text, but are often inconsistent when compared with experts. These errors can bias downstream estimates of population parameters such as regression coefficients…

Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate human…

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although these approaches…

Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. However, the auto-regressive generation process makes LLMs prone to produce errors, hallucinations and inconsistent statements when…

Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their…

Previous studies have established that language models manifest stereotyped biases. Existing debiasing strategies, such as retraining a model with counterfactual data, representation projection, and prompting often fail to efficiently…

Reasoning is a fundamental aspect of human intelligence that plays a crucial role in activities such as problem solving, decision making, and critical thinking. In recent years, large language models (LLMs) have made significant progress in…

Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models often inherit deep-rooted social biases from their training…