Related papers: User Preference Modeling for Conversational LLM Ag…

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

Aligning Large Language Models (LLMs) to cater to different human preferences, learning new skills, and unlearning harmful behavior is an important problem. Search-based methods, such as Best-of-N or Monte-Carlo Tree Search, are performant,…

A long-standing challenge in developing accurate recommendation models is simulating user behavior, mainly due to the complex and stochastic nature of user interactions. Towards this, one promising line of work has been the use of Large…

Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have enabled powerful semantic and multimodal reasoning capabilities, creating new opportunities to enhance sample efficiency, high-level planning, and…

Preference-based reinforcement learning (RL) offers a promising approach for aligning policies with human intent but is often constrained by the high cost of human feedback. In this work, we introduce PrefVLM, a framework that integrates…

Machine Learning's proliferation in critical fields such as healthcare, banking, and criminal justice has motivated the creation of tools which ensure trust and transparency in ML models. One such tool is Actionable Recourse (AR) for…

Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning from human feedback (RLHF) approaches often rely on monolithic…

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…

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…

Recommender systems have rapidly evolved and become integral to many online services. However, existing systems sometimes produce unstable and unsatisfactory recommendations that fail to align with users' fundamental and long-term…

Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is preferred over another. This limitation is especially critical…

Large language models (LLMs) exhibit enhanced capabilities in language understanding and generation. By utilizing their embedded knowledge, LLMs are increasingly used as conversational recommender systems (CRS), achieving improved…

Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation enhances LLM…

Training reinforcement learning agents with human feedback is crucial when task objectives are difficult to specify through dense reward functions. While prior methods rely on offline trajectory comparisons to elicit human preferences, such…

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

Large language models (LLMs) have shown remarkable success, but aligning them with human preferences remains a core challenge. As individuals have their own, multi-dimensional preferences, recent studies have explored multi-dimensional…

Effectively modeling the dynamic nature of user preferences is crucial for enhancing recommendation accuracy and fostering transparency in recommender systems. Traditional user profiling often overlooks the distinction between transitory…

Preference finetuning methods like Direct Preference Optimization (DPO) with AI-generated feedback have shown promise in aligning Large Vision-Language Models (LVLMs) with human preferences. However, existing techniques overlook the…

Accurately modeling user preferences is vital not only for improving recommendation performance but also for enhancing transparency in recommender systems. Conventional user profiling methods, such as averaging item embeddings, often…