相关论文: P-Check: Advancing Personalized Reward Model via L…

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Self-evaluation is increasingly central to language model training, underpinning techniques from Constitutional AI to self-refinement. We investigate whether coupling self-evaluation to reward signals creates incentives for wireheading,…

Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a…

Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial for good results -- while in principle the reward only needs…

Nowadays, training and evaluating DeepResearch-generated reports remain challenging due to the lack of verifiable reward signals. Accordingly, rubric-based evaluation has become a common practice. However, existing approaches either rely on…

Conventional reward modeling relies on gradient descent over neural weights, creating opaque, data-hungry "black boxes." We propose a paradigm shift from implicit to explicit reward parameterization, recasting optimization from continuous…

Reward modeling is essential for aligning large language models with human preferences, yet predominant architectures rely on a static pooling strategy to condense sequences into scalar scores. This paradigm, however, suffers from two key…

Design and control of autonomous systems that operate in uncertain or adversarial environments can be facilitated by formal modelling and analysis. Probabilistic model checking is a technique to automatically verify, for a given temporal…

Reinforcement Learning from Human Feedback has become the standard paradigm for language model alignment, where reward models directly determine alignment effectiveness. In this work, we focus on how to evaluate the generalizability of…

The development of trustworthy conversational information-seeking systems relies on dialogue models that can generate faithful and accurate responses based on relevant knowledge texts. However, two main challenges hinder this task. Firstly,…

Personalized generation models for a single subject have demonstrated remarkable effectiveness, highlighting their significant potential. However, when extended to multiple subjects, existing models often exhibit degraded performance,…

Process Reward Models (PRMs) have emerged as a powerful tool for providing step-level feedback when evaluating the reasoning of Large Language Models (LLMs), which frequently produce chains of thought (CoTs) containing errors even when the…

People are remarkably capable of generating their own goals, beginning with child's play and continuing into adulthood. Despite considerable empirical and computational work on goals and goal-oriented behavior, models are still far from…

Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimensions remains a persistent challenge. Though reinforcement…

Driving behavior modeling is of great importance for designing safe, smart, and personalized autonomous driving systems. In this paper, an internal reward function-based driving model that emulates the human's decision-making mechanism is…

Recent years have witnessed remarkable progress in 3D content generation. However, corresponding evaluation methods struggle to keep pace. Automatic approaches have proven challenging to align with human preferences, and the mixed…

Owing to the advancement of deep learning, artificial systems are now rival to humans in several pattern recognition tasks, such as visual recognition of object categories. However, this is only the case with the tasks for which correct…

Training reinforcement learning agents with human feedback is crucial when task objectives are difficult to specify through dense reward functions. While prior methods rely on offline trajectory comparisons to elicit human preferences, such…

We define a novel neuro-symbolic framework, argumentative reward learning, which combines preference-based argumentation with existing approaches to reinforcement learning from human feedback. Our method improves prior work by generalising…

Appropriate credit assignment for delay rewards is a fundamental challenge for reinforcement learning. To tackle this problem, we introduce a delay reward calibration paradigm inspired from a classification perspective. We hypothesize that…