Related papers: Response Time Enhances Alignment with Heterogeneou…

The SLAM paper demonstrated that on-device Small Language Models (SLMs) are a viable and cost-effective alternative to API-based Large Language Models (LLMs), such as OpenAI's GPT-4, offering comparable performance and stability. However,…

In natural human-to-human conversations, participants often receive feedback signals from one another based on their follow-up reactions. These reactions can include verbal responses, facial expressions, changes in emotional state, and…

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

Aligning agent behaviors with diverse human preferences remains a challenging problem in reinforcement learning (RL), owing to the inherent abstractness and mutability of human preferences. To address these issues, we propose AlignDiff, a…

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…

Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in user values and needs. This paper introduces a comprehensive…

Large language models (LLMs) are increasingly used to simulate human behavior, but common practices to use LLM-generated data are inefficient. Treating an LLM's output ("model choice") as a single data point underutilizes the information…

In the realm of artificial intelligence, where a vast majority of data is unstructured, obtaining substantial amounts of labeled data to train supervised machine learning models poses a significant challenge. To address this, we delve into…

We examine diverging preferences in human-labeled preference datasets. We develop a taxonomy of disagreement sources spanning ten categories across four high-level classes and find that the majority of disagreements are due to factors such…

In many industrial settings, users wish to ask questions in natural language, the answers to which require assembling information from diverse structured data sources. With the advent of Large Language Models (LLMs), applications can now…

While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority…

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between…

Using Large Language Models (LLMs) to simulate user opinions has received growing attention. Yet LLMs, especially trained with reinforcement learning from human feedback (RLHF), are known to exhibit biases toward dominant viewpoints,…

Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesis methods are computationally expensive. We propose a novel…

The drift diffusion model (DDM) is a model of sequential sampling with diffusion (Brownian) signals, where the decision maker accumulates evidence until the process hits a stopping boundary, and then stops and chooses the alternative that…

Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of…

Large language models (LLMs) have demonstrated significant capability to generalize across a large number of NLP tasks. For industry applications, it is imperative to assess the performance of the LLM on unlabeled production data from time…

Learning a reward model (RM) from human preferences has been an important component in aligning large language models (LLMs). The canonical setup of learning RMs from pairwise preference data is rooted in the classic Bradley-Terry (BT)…

The Latent Block Model (LBM) is a model-based method to cluster simultaneously the $d$ columns and $n$ rows of a data matrix. Parameter estimation in LBM is a difficult and multifaceted problem. Although various estimation strategies have…

Human Label Variation (HLV), i.e. systematic differences among annotators' judgments, remains underexplored in benchmarks despite rapid progress in large language model (LLM) development. We address this gap by introducing an evaluation…