相关论文: Training AI Co-Scientists Using Rubric Rewards

The advent of large pre-trained generative language models has provided a common framework for AI story generation via sampling the model to create sequences that continue the story. However, sampling alone is insufficient for story…

Reward modeling lies at the core of reinforcement learning from human feedback (RLHF), yet most existing reward models rely on scalar or pairwise judgments that fail to capture the multifaceted nature of human preferences. Recent studies…

Over the past year, artificial intelligence (AI) companies have been increasingly adopting AI safety frameworks. These frameworks outline how companies intend to keep the potential risks associated with developing and deploying frontier AI…

Scientific research proceeds through iterative cycles of hypothesis generation, experiment design, execution, and revision. AI agents can automate parts of this process, but existing approaches typically follow a single research trajectory…

Large language models (LLMs) are increasingly used as evaluators for natural language generation, applying human-defined rubrics to assess system outputs. However, human rubrics are often static and misaligned with how models internally…

Wide usage of ChatGPT has highlighted the potential of reinforcement learning from human feedback. However, its training pipeline relies on manual ranking, a resource-intensive process. To reduce labor costs, we propose a self-supervised…

Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and supporting innovative approaches in various scientific fields. In this…

This paper introduces a framework for the automated evaluation of natural language texts. A manually constructed rubric describes how to assess multiple dimensions of interest. To evaluate a text, a large language model (LLM) is prompted…

College students face well-being challenges driven by academic pressure, financial strain, and social expectations. While campus counseling and student-success programs offer support, access is often limited by stigma, waitlists, and…

The use of artificial intelligence (AI) in research across all disciplines is becoming ubiquitous. However, this ubiquity is largely driven by hyperspecific AI models developed during scientific studies for accomplishing a well-defined,…

Despite its size and complexity, the human cortex exhibits striking anatomical regularities, suggesting there may simple meta-algorithms underlying cortical learning and computation. We expect such meta-algorithms to be of interest since…

This study demonstrates the application of instruction finetuning of pretrained Large Language Models (LLMs) to automate the generation of AI research leaderboards, extracting (Task, Dataset, Metric, Score) quadruples from articles. It aims…

AI Scientists have shown promising progress across multiple stages of the research pipeline, among which automatic scientific paper writing remains a formidable challenge. The Introduction writing is especially challenging, which demands…

Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes definitive truth judgments. This paper introduces a novel framework in which AI models…

Artificial intelligence (AI) tools are being incorporated into scientific research workflows with the potential to enhance efficiency in tasks such as document analysis, question answering (Q&A), and literature search. However, system…

As large language models (LLMs) advance, the ultimate vision for their role in science is emerging: we could build an AI collaborator to effectively assist human beings throughout the entire scientific research process. We refer to this…

Creating high-quality figures and visualizations for scientific papers is a time-consuming task that requires both deep domain knowledge and professional design skills. Despite over 2.5 million scientific papers published annually, the…

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise…

Reinforcement learning algorithms use correlations between policies and rewards to improve agent performance. But in dynamic or sparsely rewarding environments these correlations are often too small, or rewarding events are too infrequent…

Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-ended instruction following. To address this limitation, we…