相关论文: Quantifying and Optimizing Global Faithfulness in …

As a typical open-ended generation task, creative writing lacks verifiable reference answers, which has long constrained reward modeling and automatic evaluation due to high human annotation costs, evaluative bias, and coarse feedback…

Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of…

Although risk awareness is fundamental to an online operating agent, it has received less attention in the challenging continuous domain and under partial observability. This paper presents a novel formulation and solution for risk-averse…

Effective persuasive dialogue agents adapt their strategies to individual users, accounting for the evolution of their psychological states and intentions throughout conversations. We present a personality-aware reinforcement learning…

Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based…

There are growing concerns about the risks posed by AI companion applications designed for emotional engagement. Existing safety evaluations often rely on self-reported user data or interviews, offering limited insights into real-time…

Faithfully personalizing large language models (LLMs) to align with individual user preferences is a critical but challenging task. While supervised fine-tuning (SFT) quickly reaches a performance plateau, standard reinforcement learning…

Hierarchical predictive processing explains adaptive behaviour through precision-weighted inference. Explicit belief revision often fails to produce corresponding changes in stress reactivity or autonomic regulation. This asymmetry suggests…

Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true decision process, undermining reliability and trust. We introduce a formal framework for reasoning…

As an autonomous system performs a task, it should maintain a calibrated estimate of the probability that it will achieve the user's goal. If that probability falls below some desired level, it should alert the user so that appropriate…

Large language models are increasingly deployed in high-stakes tasks, where confident yet incorrect inferences may cause severe real-world harm, bringing the previously overlooked issue of confidence faithfulness back to the forefront. A…

Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. This raises questions…

Peer prediction mechanisms incentivize agents to truthfully report their signals even in the absence of verification by comparing agents' reports with those of their peers. In the detail-free multi-task setting, agents respond to multiple…

Explainability algorithms aimed at interpreting decision-making AI systems usually consider balancing two critical dimensions: 1) \textit{faithfulness}, where explanations accurately reflect the model's inference process. 2)…

We consider the setting of stochastic multiagent systems modelled as stochastic multiplayer games and formulate an automated verification framework for quantifying and reasoning about agents' trust. To capture human trust, we work with a…

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…

AI systems increasingly assist human decision making by producing preliminary assessments of complex inputs. However, such AI-generated assessments can often be noisy or systematically biased, raising a central question: how should costly…

This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models. The first contribution addresses constrained Markov…

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

A growing body of research has explored how to support humans in making better use of AI-based decision support, including via training and onboarding. Existing research has focused on decision-making tasks where it is possible to evaluate…