Related papers: LATTE: Forecasting Peer Anchored Preference Trajec…

As Large Language Models (LLMs) advance, personalization has become a key mechanism for tailoring outputs to individual user needs. However, most existing methods rely heavily on dense interaction histories, making them ineffective in…

Learning clients embeddings from sequences of their historic communications is central to financial applications. While large language models (LLMs) offer general world knowledge, their direct use on long event sequences is computationally…

Current human-AI alignment and evaluation methods for large language models (LLMs) often rely on preference signals collected immediately after an interaction. This practice implicitly treats preference as static, even though many…

Modern transformer-based sequential recommenders excel at capturing short-term intent but often suffer from recency bias, overlooking stable long-term preferences. While extending sequence lengths is an intuitive fix, it is computationally…

With the increasing demands on e-commerce platforms, numerous user action history is emerging. Those enriched action records are vital to understand users' interests and intents. Recently, prior works for user behavior prediction mainly…

Accommodating human preferences is essential for creating AI agents that deliver personalized and effective interactions. Recent work has shown the potential for LLMs to infer preferences from user interactions, but they often produce broad…

Test-time adaptation with pre-trained vision-language models has gained increasing attention for addressing distribution shifts during testing. Among these approaches, memory-based algorithms stand out due to their training-free nature and…

Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decoding time with implicit user preferences. Traditional…

This paper proposes Text mAtching based SequenTial rEcommendation model (TASTE), which maps items and users in an embedding space and recommends items by matching their text representations. TASTE verbalizes items and user-item interactions…

Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or require pre-trained…

Large Language Models (LLMs) have been widely applied across multiple domains for their broad knowledge and strong reasoning capabilities. However, applying them to recommendation systems is challenging since it is hard for LLMs to extract…

Personalization is a core capability across consumer technologies, streaming, shopping, wearables, and voice, yet it remains challenged by sparse interactions, fast content churn, and heterogeneous textual signals. We present RecMind, an…

The matrix factorization (MF) technique has been widely adopted for solving the rating prediction problem in recommender systems. The MF technique utilizes the latent factor model to obtain static user preferences (user latent vectors) and…

Typical LLM responses tend to follow a default style, even though users often have distinct preferences regarding tone, verbosity, and formality that they do not explicitly state in their prompts. Evaluating whether personalization methods…

Achieving personalized alignment requires adapting large language models to each user's evolving context. While decoding-time personalization offers a scalable alternative to training-time methods, existing methods largely rely on implicit,…

Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In…

Proactively predicting a users next utterance in human-machine dialogue can streamline interaction and improve user experience. Existing commercial API-based solutions are subject to privacy concerns while deploying general-purpose LLMs…

Users often omit essential details in their requests to LLM-based agents, resulting in under-specified inputs for tool use. This poses a fundamental challenge for tool-augmented agents, as API execution typically requires complete…

User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet how to reliably leverage preference signals for answer generation remains under-explored. In practice, preferences can be noisy, incomplete, or…

Recent research has increasingly focused on evaluating large language models' (LLMs) alignment with diverse human values and preferences, particularly for open-ended tasks like story generation. Traditional evaluation metrics rely heavily…