Related papers: Whose Boat Does it Float? Improving Personalizatio…
Personalization is well studied in search and recommendation, but personalized question answering remains underexplored due to challenges in inferring preferences from long, noisy, implicit contexts and generating responses that are both…
As artificial intelligence (AI) systems, particularly large language models (LLMs), become increasingly integrated into decision-making processes, the ability to trust their outputs is crucial. To earn human trust, LLMs must be well…
Large Language Model (LLM)-powered web GUI agents are increasingly automating everyday online tasks. Despite their popularity, little is known about how users' preferences and values impact agents' reasoning and behavior. In this work, we…
Human-in-the-loop reinforcement learning allows the training of agents through various interfaces, even for non-expert humans. Recently, preference-based methods (PbRL), where the human has to give his preference over two trajectories,…
Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…
Large language models (LLMs) are revolutionizing every aspect of society. They are increasingly used in problem-solving tasks to substitute human assessment and reasoning. LLMs are trained on what humans write and are thus exposed to human…
We study interactive learning of LLM-based language agents based on user edits made to the agent's output. In a typical setting such as writing assistants, the user interacts with a language agent to generate a response given a context, and…
This study examines the understudied role of algorithmic evaluation of human judgment in hybrid decision-making systems, a critical gap in management research. While extant literature focuses on human reluctance to follow algorithmic…
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…
Language models (LMs) trained on vast quantities of text data can acquire sophisticated skills such as generating summaries, answering questions or generating code. However, they also manifest behaviors that violate human preferences, e.g.,…
Personalization has traditionally depended on platform-specific user models that are optimized for prediction but remain largely inaccessible to the people they describe. As LLM-based assistants increasingly mediate search, shopping,…
User preference learning is generally a hard problem. Individual preferences are typically unknown even to users themselves, while the space of choices is infinite. Here we study user preference learning from information-theoretic…
Recent advancements in Large Language Models (LLMs) have demonstrated exceptional performance across a wide range of tasks, generating significant interest in their application to recommendation systems. However, existing methods have not…
Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…
With the rise in capabilities of large language models (LLMs) and their deployment in real-world tasks, evaluating LLM alignment with human preferences has become an important challenge. Current benchmarks average preferences across all…
A prominent issue in aligning language models (LMs) to personalized preferences is underspecification -- the lack of information from users about their preferences. A popular trend of injecting such specification is adding a prefix (e.g.…
Designers of digital solutions increasingly consult Large Language Models (LLMs) for their work. However, it remains unclear how this may affect the user experiences they produce and there are no established practices. We investigate how…
This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock…
As large language models (LLMs) enter the mainstream, aligning them to foster constructive dialogue rather than exacerbate societal divisions is critical. Using an individualized and multicultural alignment dataset of over 7,500…
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…