Related papers: Understanding and Mitigating Bias Inheritance in L…

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases, raising fairness concerns. Existing debiasing methods, such…

Current multimodal language model (MLM) training approaches overlook the influence of instruction templates. Previous research deals with this problem by leveraging hand-crafted or model-generated templates, failing to investigate the…

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Large language models (LLMs) are increasingly deployed in high-stakes hiring applications, making decisions that directly impact people's careers and livelihoods. While prior studies suggest simple anti-bias prompts can eliminate…

Many recent papers have studied the development of superforecaster-level event forecasting LLMs. While methodological problems with early studies cast doubt on the use of LLMs for event forecasting, recent studies with improved evaluation…

Confirmation bias, the tendency to seek evidence that supports rather than challenges one's belief, hinders one's reasoning ability. We examine whether large language models (LLMs) exhibit confirmation bias by adapting the rule-discovery…

The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption. While the pre-trained models can perform many tasks, such models are often fine-tuned to improve their performance on…

Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question for math reasoning via an empirical study, followed by…

Large Language Models (LLMs) have advanced various Natural Language Processing (NLP) tasks, such as text generation and translation, among others. However, these models often generate texts that can perpetuate biases. Existing approaches to…

Data augmentation is a critical component of deep learning pipelines, enhancing model generalization by increasing dataset diversity. Traditional augmentation strategies rely on manually designed transformations, stochastic sampling, or…

The rapid progress of large language models (LLMs) is fueled by the growing reliance on datasets that blend real and synthetic data. While synthetic data offers scalability and cost-efficiency, it often introduces systematic distributional…

With the evolution of large language models (LLMs), their robustness against individual simple biases has been enhanced. However, we observe that the ensemble of multiple simple biases still exerts a significant adverse impact on LLMs.…

Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data, leading to impressive performance across a range of downstream applications. Current methods often rely on human-annotated…

Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…

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…

Numerous methods have been proposed to measure LLM misgendering, including probability-based evaluations (e.g., automatically with templatic sentences) and generation-based evaluations (e.g., with automatic heuristics or human validation).…

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…

Researchers have proposed the use of generative large language models (LLMs) to label data for research and applied settings. This literature emphasizes the improved performance of these models relative to other natural language models,…

Despite advances in large language models (LLMs) on reasoning and instruction-following tasks, it is unclear whether they can reliably produce outputs aligned with a variety of user goals, a concept called steerability. Two gaps in current…

To mitigate gender bias in contextualized language models, different intrinsic mitigation strategies have been proposed, alongside many bias metrics. Considering that the end use of these language models is for downstream tasks like text…