OpenAI's recent introduction of Reinforcement Fine-Tuning (RFT) showcases the potential of reasoning foundation model and offers a new paradigm for fine-tuning beyond simple pattern imitation. This technical report presents OpenRFT, our attempt to fine-tune generalist reasoning models for domain-specific tasks under the same settings as RFT. The evaluation is conducted on Sci-KnowEval, where OpenRFT achieves notable performance gains with only 100 domain-specific samples for each task. More experimental results will be updated continuously in later versions. OpenAI's o1 model has shown strong reasoning abilities in mathematics and programming, but its generalization to other tasks remains uncertain. The recent introduction of Reinforcement Fine-Tuning (RFT) (OpenAI, 2024) has provided a promising avenue for reasoning generalization. With only dozens of high-quality (question, answer) pairs, RFT enables the creation of customized reasoning models excelling at domain-specific tasks. The significance of RFT is at least two-fold: (1) It demonstrates the promise of using generalist reasoning models, like o1, as reasoning foundation models. By enabling the efficient creation of domain-specific reasoning models, RFT practically expands the applicability of reasoning models across diverse tasks. Unlike Supervised Fine-Tuning (SFT), which merely mimics patterns in training data, RFT leverages reasoning capabilities to facilitate thinking and trial-and-error learning.

The technical report introduces O1-CODER, an attempt to replicate OpenAI's o1 model with a focus on coding tasks. It integrates reinforcement learning (RL) and Monte Carlo Tree Search (MCTS) to enhance the model's System-2 thinking capabilities. The framework includes training a Test Case Generator (TCG) for standardized code testing, using MCTS to generate code data with reasoning processes, and iteratively fine-tuning the policy model to initially produce pseudocode and then generate the full code. The report also addresses the opportunities and challenges in deploying o1-like models in real-world applications, suggesting transitioning to the System-2 paradigm and highlighting the imperative for world model construction. Updated model progress and experimental results will be reported in subsequent versions. OpenAI recently introduced the o1 model (OpenAI, 2024), which has demonstrated impressive system-2 thinking capabilities. This model represents a significant advancement in AI's ability to perform complex reasoning tasks that require higher-order cognitive functions. Following its release, numerous analysis and replication efforts have emerged, demonstrating the growing interest in reasoning models. Prior to the o1 model, large language models (LLMs) primarily exhibited System-1 capabilities, characterized by fast, intuitive responses.

Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of pre-trained datasets, CLIP suffers from the bias problem in real-world applications. Existing debiasing methods struggle to obtain sufficient image samples for minority groups and incur high costs for group labeling. To address the limitations, we propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases. Specifically, this approach repurposes the text encoder to function as an image encoder, thereby eliminating the need for image data. Simultaneously, it utilizes a large language model (LLM) to generate a balanced text dataset, which is then used for prompt tuning. However, we observed that the model overfits to the text modality because label names, serving as supervision signals, appear explicitly in the texts. To address this issue, we further introduce a Multi-Target Prediction (MTP) task that motivates the model to focus on complex contexts and distinguish between target and biased information. Extensive experiments on the Waterbirds and CelebA datasets show that our method significantly improves group robustness, achieving state-of-the-art results among image-free methods and even competitive performance compared to image-supervised methods. Furthermore, the proposed method can be adapted to challenging scenarios with multiple or unknown bias attributes, demonstrating its strong generalization and robustness.

Recent studies have demonstrated that large language models (LLMs) are susceptible to being misled by false premise questions (FPQs), leading to errors in factual knowledge, know as factuality hallucination. Existing benchmarks that assess this vulnerability primarily rely on manual construction, resulting in limited scale and lack of scalability. In this work, we introduce an automated, scalable pipeline to create FPQs based on knowledge graphs (KGs). The first step is modifying true triplets extracted from KGs to create false premises. Subsequently, utilizing the stateof-the-art capabilities of GPTs, we generate semantically rich FPQs. Based on the proposed method, we present a comprehensive benchmark, the Knowledge Graph-based False Premise Questions (KG-FPQ), which contains approximately 178k FPQs across three knowledge domains, at six levels of confusability, and in two task formats. Using KG-FPQ, we conduct extensive evaluations on several representative LLMs and provide valuable insights. The KG-FPQ dataset and code are available Figure 1: Top: LLM correctly answers when faced with at https://github.com/yanxuzhu/KG-FPQ. a TPQ. Middle: LLM experiences factuality hallucination when faced with a FPQ.

This paper presents a follow-up study to OpenAI's recent superalignment work on Weak-to-Strong Generalization (W2SG). Superalignment focuses on ensuring that high-level AI systems remain consistent with human values and intentions when dealing with complex, high-risk tasks. The W2SG framework has opened new possibilities for empirical research in this evolving field. Our study simulates two phases of superalignment under the W2SG framework: the development of general superhuman models and the progression towards superintelligence. In the first phase, based on human supervision, the quality of weak supervision is enhanced through a combination of scalable oversight and ensemble learning, reducing the capability gap between weak teachers and strong students. In the second phase, an automatic alignment evaluator is employed as the weak supervisor. By recursively updating this auto aligner, the capabilities of the weak teacher models are synchronously enhanced, achieving weak-to-strong supervision over stronger student models.We also provide an initial validation of the proposed approach for the first phase. Using the SciQ task as example, we explore ensemble learning for weak teacher models through bagging and boosting. Scalable oversight is explored through two auxiliary settings: human-AI interaction and AI-AI debate. Additionally, the paper discusses the impact of improved weak supervision on enhancing weak-to-strong generalization based on in-context learning. Experiment code and dataset will be released at https://github.com/ADaM-BJTU/W2SG.