Related papers: Quantifying and Optimizing Global Faithfulness in …
Faithfulness is arguably the most critical metric to assess the reliability of explainable AI. In NLP, current methods for faithfulness evaluation are fraught with discrepancies and biases, often failing to capture the true reasoning of…
The utility of Role-Playing Language Agents in sociological research is growing alongside the adoption of Large Language Models. For realism in social simulation, these agents must adhere to their personas defined by character profiles, yet…
As artificial intelligence transforms software development, a critical question emerges: how can developers and AI systems collaborate most effectively? This dissertation optimizes human-AI programming roles through self-determination…
Recent advancements in deep reinforcement learning have brought forth an impressive display of highly skilled artificial agents capable of complex intelligent behavior. In video games, these artificial agents are increasingly deployed as…
Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem-centric…
Recent years have witnessed the emergence of a variety of post-hoc interpretations that aim to uncover how natural language processing (NLP) models make predictions. Despite the surge of new interpretation methods, it remains an open…
The emerging large language model role-playing agents (LLM RPAs) aim to simulate individual human behaviors, but the persona fidelity is often undermined by manually-created profiles (e.g., cherry-picked information and personality…
Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned behavior: the same query may call for different planning…
Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…
Large language models (LLMs) have demonstrated significant potential in developing Role-Playing Agents (RPAs). However, current research primarily evaluates RPAs using famous fictional characters, allowing models to rely on memory…
Explainability remains a critical challenge in artificial intelligence (AI) systems, particularly in high stakes domains such as healthcare, finance, and decision support, where users must understand and trust automated reasoning.…
Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making problems. However, existing DRL agents make decisions in an opaque fashion, hindering the user from establishing trust and scrutinizing…
Recent approaches in personalized reward modeling have primarily focused on leveraging user interaction history to align model judgments with individual preferences. However, existing approaches largely treat user context as a static or…
Current role-playing agents (RPAs) are typically constructed by imitating surface-level behaviors, but this approach lacks internal cognitive consistency, often causing out-of-character errors in complex situations. To address this, we…
Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response…
Aligning large language models (LLMs) typically aim to reflect general human values and behaviors, but they often fail to capture the unique characteristics and preferences of individual users. To address this gap, we introduce the concept…
Since 2022, AI-powered coding assistants have produced contradictory evidence: controlled studies report 20-56% productivity gains on well-scoped tasks, while the most rigorous RCT documents a 19% slowdown for experienced developers, and…
The rapid adoption of Large Language Models (LLMs) in interactive systems has enabled the creation of dynamic, open-ended Role-Playing Agents (RPAs). However, evaluating these agents remains a significant challenge, as standard NLP metrics…
The integration of artificial intelligence across multiple domains has emphasized the importance of replicating human-like cognitive processes in AI. By incorporating emotional intelligence into AI agents, their emotional stability can be…
This paper introduces a new dimension for validating algorithmic decisions about humans by measuring the fidelity of their representations. Representation Fidelity measures if decisions about a person rest on reasonable grounds. We propose…