Related papers: How Does Personalized Memory Shape LLM Behavior? B…

The rapid development of language models (LMs) brings unprecedented accessibility and usage for both models and users. On the one hand, powerful LMs achieve state-of-the-art performance over numerous downstream NLP tasks. On the other hand,…

Recent advances in Large Language Models (LLMs) have generated significant interest in their capacity to simulate human-like behaviors, yet most studies rely on fictional personas rather than actual human data. We address this limitation by…

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…

This paper presents a novel approach to aligning large language models (LLMs) with individual human preferences, sometimes referred to as Reinforcement Learning from \textit{Personalized} Human Feedback (RLPHF). Given stated preferences…

Memorization of the relation between entities in a dataset can lead to privacy issues when using a trained model for question answering. We introduce Relational Memorization (RM) to understand, quantify and control this phenomenon. While…

As large language models (LLMs) become increasingly integrated into daily life, there is growing demand for AI assistants that are not only reactive but also proactive and personalized. While recent advances have pushed forward proactivity…

Existing benchmarks for large language models (LLMs) predominantely focus on assessing their capabilities through verifiable tasks. Such objective and static benchmarks offer limited utility for practical LLM selection, making it difficult…

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…

Personalization in social robotics is critical for fostering effective human-robot interactions, yet systems often face the cold start problem, where initial user preferences or characteristics are unavailable. This paper proposes a novel…

Recent advances in large language models (LLMs) have increasingly relied on reinforcement learning (RL) to improve their reasoning capabilities. Three types of approaches have been widely adopted: The first relies on a deep neural network…

Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test a angent's ability to passively retrieve…

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…

Self-preference is a fundamental feature of biological organisms. Since large language models (LLMs) lack sentience, they might be expected to avoid such distortions. Yet, across 72 experiments and ~41,000 queries, we discovered massive…

Stated preference (SP) surveys are a key method to research how individuals make trade-offs in hypothetical, also futuristic, scenarios. In energy context this includes key decarbonisation enablement contexts, such as low-carbon…

Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This \textit{motivated reasoning} at a collective level can be detrimental to society when…

Aligning large language models (LLMs) with human preferences has been recognized as the key to improving LLMs' interaction quality. However, in this pluralistic world, human preferences can be diversified due to annotators' different…

As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we…

Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity, known as working memory, is fundamental to human reasoning and intelligence. Despite…

Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact…

Large language models (LLMs) often generate natural language rationales -- free-form explanations that help improve performance on complex reasoning tasks and enhance interpretability for human users. However, evaluating these rationales…