相关论文: Improving the Distributional Alignment of LLMs usi…

The guidance from capability evaluations has greatly propelled the progress of both human society and Artificial Intelligence. However, as LLMs evolve, it becomes challenging to construct evaluation benchmarks for them with accurate labels…

Large language models (LLMs) have demonstrated their remarkable capacity across a variety of tasks. However, reasoning remains a challenge for LLMs. To improve LLMs' reasoning ability, process supervision has proven to be better than…

Tabular data synthesis is crucial in machine learning, yet existing general methods-primarily based on statistical or deep learning models-are highly data-dependent and often fall short in recommender systems. This limitation arises from…

The success of AI assistants based on language models (LLMs) hinges crucially on Reinforcement Learning from Human Feedback (RLHF), which enables the generation of responses more aligned with human preferences. As universal AI assistants,…

Through the lense of multilevel model (MLM) specification and regularization, this is a connect-the-dots introductory summary of Small Area Estimation, e.g. small group prediction informed by a complex sampling design. While a comprehensive…

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to individual preferences while maintaining alignment with…

Introduction. Advances in large language models (LLMs) offer a chance to act as scientific assistants, helping people grasp complex research areas. This study examines how LLMs evolve in healthcare disparities research, with attention to…

Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory. Motivated by considerations of multi-group fairness, we seek KL divergence…

Large Language Models (LLMs) are often misleadingly recognized as having a personality or a set of values. We argue that an LLM can be seen as a superposition of perspectives with different values and personality traits. LLMs exhibit…

As large language models (LLMs) become integral to intelligent user interfaces (IUIs), their role as decision-making agents raises critical concerns about alignment. Although extensive research has addressed issues such as factuality, bias,…

Alignment of large language models (LLMs) with human values and preferences, often achieved through fine-tuning based on human feedback, is essential for ensuring safe and responsible AI behaviors. However, the process typically requires…

Serendipity plays a pivotal role in enhancing user satisfaction within recommender systems, yet its evaluation poses significant challenges due to its inherently subjective nature and conceptual ambiguity. Current algorithmic approaches…

Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using…

Alignment of Large Language Models (LLMs) remains an unsolved problem. Human preferences are highly distributed and can be captured at multiple levels of abstraction, from the individual to diverse populations. Organisational preferences,…

The spread of media bias is a significant concern as political discourse shapes beliefs and opinions. Addressing this challenge computationally requires improved methods for interpreting news. While large language models (LLMs) can scale…

Large language models (LLMs) often reflect real-world biases, leading to efforts to mitigate these effects and make the models unbiased. Achieving this goal requires defining clear criteria for an unbiased state, with any deviation from…

State of the art large language models (LLMs) have shown impressive performance on a variety of benchmark tasks and are increasingly used as components in larger applications, where LLM-based predictions serve as proxies for human…

Preference alignment aims to guide generative models by learning from comparisons between preferred and non-preferred samples. In practice, most existing approaches rely on preference pairs constructed from model-generated images. Such…

Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the user's intent. Existing approaches to semi-supervised…

Large language models (LLMs) are increasingly used to predict human behavior. We propose a measure for evaluating how much knowledge a pretrained LLM brings to such a prediction: its equivalent sample size, defined as the amount of…