Related papers: Anyprefer: An Agentic Framework for Preference Dat…
Recent years have witnessed remarkable progress in 3D content generation. However, corresponding evaluation methods struggle to keep pace. Automatic approaches have proven challenging to align with human preferences, and the mixed…
Customizing robotic behaviors to be aligned with diverse human preferences is an underexplored challenge in the field of embodied AI. In this paper, we present Promptable Behaviors, a novel framework that facilitates efficient…
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…
Preferences play a key role in determining what goals/constraints to satisfy when not all constraints can be satisfied simultaneously. In this work, we study preference-based planning in a stochastic system modeled as a Markov decision…
Artificial Intelligence (AI) advancement is heavily dependent on access to large-scale, high-quality training data. However, in specialized domains such as healthcare, data acquisition faces significant constraints due to privacy…
Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between patient needs and the availability of mental health support. However, current LLMs struggle…
Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models (LMs). Despite its widespread use, the way preference-based learning is applied varies wildly,…
High-quality preference datasets are essential for training reward models that can effectively guide large language models (LLMs) in generating high-quality responses aligned with human preferences. As LLMs become stronger and better…
Preference-based reinforcement learning (PbRL) is the dominant framework for aligning AI systems to human preferences. However, evaluation protocols for such data were designed for text and have not been validated for speech. We present the…
Many decision-making problems feature multiple objectives. In such problems, it is not always possible to know the preferences of a decision-maker for different objectives. However, it is often possible to observe the behavior of…
Current instruction-tuned language models are exclusively trained with textual preference data and thus are often not aligned with the unique requirements of other modalities, such as speech. To better align language models with the speech…
Current frameworks for consensus statement generation with large language models lack the inherent structure needed to provide provable fairness guarantees when aggregating diverse free-form opinions. We model the task as a multi-objective,…
Aligning pretrained language models (LMs) often requires large-scale preference data and substantial computational resources. These costs become even more prohibitive for multi-objective or pluralistic alignment. Is this truly necessary?…
Many real-world eligibility problems, ranging from medical diagnosis to tax planning, can be mapped to decision problems expressed in natural language, wherein a model must make a binary choice based on user features. Large-scale domains…
Prior work establishes that controlled contrastiveness between self-generated responses from large language models, set via reward scores, improves downstream preference tuning in English. We extend this method to multiple languages and…
We propose a new framework for imitation learning -- treating imitation as a two-player ranking-based game between a policy and a reward. In this game, the reward agent learns to satisfy pairwise performance rankings between behaviors,…
A key distinguishing feature of conversational recommender systems over traditional recommender systems is their ability to elicit user preferences using natural language. Currently, the predominant approach to preference elicitation is to…
User satisfaction in dialogue systems is inherently subjective. When the same response strategy is applied across users, minority users may assign different satisfaction ratings than majority users due to variations in individual intents…
In the RAG paradigm, the information retrieval module provides context for generators by retrieving and ranking multiple documents to support the aggregation of evidence. However, existing ranking models are primarily optimized for…
Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…