Related papers: One Model for All: Multi-Objective Controllable La…

Large language model (LLM) personalization aims to tailor model behavior to individual users based on their historical interactions. However, its effectiveness is often hindered by two key challenges: the \textit{cold-start problem}, where…

Multimodal Large Language Models (MLLMs) excel in generating responses based on visual inputs. However, they often suffer from a bias towards generating responses similar to their pretraining corpus, overshadowing the importance of visual…

Aligning language models (LMs) to human preferences has emerged as a critical pursuit, enabling these models to better serve diverse user needs. Existing methods primarily focus on optimizing LMs for a single reward function, limiting their…

Reinforcement learning (RL) has significantly advanced the control of physics-based and robotic characters that track kinematic reference motion. However, methods typically rely on a weighted sum of conflicting reward functions, requiring…

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often fail to adequately represent diverse viewpoints. We…

Self-play methods have demonstrated remarkable success in enhancing model capabilities across various domains. In the context of Reinforcement Learning from Human Feedback (RLHF), self-play not only boosts Large Language Model (LLM)…

Learning from human feedback has been shown to be effective at aligning language models with human preferences. Past work has often relied on Reinforcement Learning from Human Feedback (RLHF), which optimizes the language model using reward…

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance, yet strict data-sharing constraints render centralized training infeasible. Federated Learning mitigates this issue by enabling…

Effective conversational agents like large language models (LLMs) must personalize their interactions to adapt to user preferences, personalities, and attributes across diverse domains like education and healthcare. Current methods like…

Aligning large language models (LLMs) to simultaneously satisfy multiple objectives remains a significant challenge, especially given the diverse and often conflicting nature of human preferences. Existing alignment methods struggle to…

The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these…

Reinforcement learning from human feedback (RLHF) is widely used to train large language models (LLMs). However, it is unclear whether LLMs accurately learn the underlying preferences in human feedback data. We coin the term \textit{Learned…

Conversational Recommender Systems (CRSs) leverage natural language interactions for personalized recommendation, yet information-scarce dialogue histories and single-turn recommendation paradigms may severely hinder accurate modeling of…

Current multimodal Large Language Models (MLLMs) suffer from ``hallucination'', occasionally generating responses that are not grounded in the input images. To tackle this challenge, one promising path is to utilize reinforcement learning…

Aligning large language models (LLMs) with human preferences remains a key challenge in AI. Preference-based optimization methods, such as Reinforcement Learning with Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on…

Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context…

Before being deployed for user-facing applications, developers align Large Language Models (LLMs) to user preferences through a variety of procedures, such as Reinforcement Learning From Human Feedback (RLHF) and Direct Preference…

This paper studies post-training large language models (LLMs) using preference feedback from a powerful oracle to help a model iteratively improve over itself. The typical approach for post-training LLMs involves Reinforcement Learning from…