Related papers: Quantifying and Optimizing Global Faithfulness in …

Prevailing alignment methods target a fixed set of preferences and therefore risk forcing value lock-in as societal norms evolve over time. We introduce Adaptive Pluralistic Alignment (APA), a modular pipeline for updating pluralistically…

Ensuring persona fidelity in large language models (LLMs) is essential for maintaining coherent and engaging human-AI interactions. However, LLMs often exhibit Out-of-Character (OOC) behavior, where generated responses deviate from an…

As artificial intelligence (AI) systems become increasingly integrated into various domains, ensuring that they align with human values becomes critical. This paper introduces a novel formalism to quantify the alignment between AI systems…

Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However,…

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information.…

Recent research on model interpretability in natural language processing extensively uses feature scoring methods for identifying which parts of the input are the most important for a model to make a prediction (i.e. explanation or…

Is explainability a false promise? This debate has emerged from the insufficient evidence that explanations help people in situations they are introduced for. More human-centered, application-grounded evaluations of explanations are needed…

A multitude of explainability methods and associated fidelity performance metrics have been proposed to help better understand how modern AI systems make decisions. However, much of the current work has remained theoretical -- without much…

Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free.…

AI alignment in the shape of Reinforcement Learning from Human Feedback (RLHF) is increasingly treated as a crucial ingredient for high performance large language models. Proximal Policy Optimization (PPO) has been positioned by recent…

Evaluating the efficiency of human-AI interactions is challenging, including subjective and objective quality aspects. With the focus on the human experience of the explanations, evaluations of explanation methods have become mostly…

Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills. However, simulating sensitive interactions, such as in mental health, is challenging. Privacy concerns restrict data…

Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in…

This report investigates approaches for prompting a tool-augmented large language model (LLM) to act as a role-playing dialogue agent in the API track of the Commonsense Persona-grounded Dialogue Challenge (CPDC) 2025. In this setting,…

Traditional ethical frameworks often struggle to model decision-making under uncertainty, treating it as a simple constraint on action. This paper introduces the Principle of Proportional Duty (PPD), a novel framework that models how…

The low-intrusion and automated personality assessment is receiving increasing attention in psychology and human-computer interaction fields. This study explores an interactive approach for personality assessment, focusing on the…

As we consider entrusting Large Language Models (LLMs) with key societal and decision-making roles, measuring their alignment with human cognition becomes critical. This requires methods that can assess how these systems represent…

Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by our interactions with AI systems themselves. To clarify the consequences of incorrectly…

Personalized AI agents are becoming central to modern information retrieval, yet most evaluation methodologies remain static, relying on fixed benchmarks and one-off metrics that fail to reflect how users' needs evolve over time. These…

Assistive agents should be able to perform under-specified long-horizon tasks while respecting user preferences. We introduce Actively Discovering and Adapting to Preferences for any Task (ADAPT) -- a benchmark designed to evaluate agents'…