Related papers: Rewarding Intellectual Humility Learning When Not …
Reinforcement Learning (RL) has shown promise in improving the reasoning abilities of Large Language Models (LLMs). However, the specific challenges of adapting RL to multimodal data and formats remain relatively unexplored. In this work,…
Variation in human annotation (i.e., disagreements) is common in NLP, often reflecting important information like task subjectivity and sample ambiguity. Modeling this variation is important for applications that are sensitive to such…
Reinforcement learning with verifiable rewards (RLVR) is a simple but powerful paradigm for training LLMs: sample a completion, verify it, and update. In practice, however, the verifier is almost never clean--unit tests probe only limited…
While reinforcement learning has advanced the reasoning abilities of Large Language Models (LLMs), these gains are largely confined to English, creating a significant performance disparity across languages. To address this, we introduce…
Reinforcement Fine-Tuning (RFT) with verifiable rewards has advanced large language models but remains underexplored for Vision-Language (VL) models. The Vision-Language Reward Model (VL-RM) is key to aligning VL models by providing…
The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…
Recently DeepSeek R1 demonstrated how reinforcement learning with simple rule-based incentives can enable autonomous development of complex reasoning in large language models, characterized by the "aha moment", in which the model manifest…
Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level performance in some specific domains via RLVR, such as…
Reinforcement learning with verifiable rewards (RLVR) has shown great potential to enhance the reasoning ability of large language models (LLMs). However, due to the limited amount of information provided during the RLVR process, the model…
Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…
Abstention Ability (AA) is a critical aspect of Large Language Model (LLM) reliability, referring to an LLM's capability to withhold responses when uncertain or lacking a definitive answer, without compromising performance. Although…
Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating…
Reinforcement Learning from Verifiable Rewards (RLVR) trains large language models (LLMs) from sampled trajectories, making decoding strategy a core component of learning rather than a purely inference-time choice. Sampling temperature…
The evaluation and post-training of large language models (LLMs) rely on supervision, but strong supervision for difficult tasks is often unavailable, especially when evaluating frontier models. In such cases, models are demonstrated to…
Reinforcement Learning with Verifiable Rewards (RLVR) has markedly improved the performance of Large Language Models (LLMs) on tasks requiring multi-step reasoning. However, most RLVR pipelines rely on sparse outcome-based rewards,…
Evaluation using Large Language Model (LLM) judges has been widely adopted in English and shown to be effective for automatic evaluation. However, their performance does not generalize well to non-English settings, and it remains unclear…
Large language models can generate solutions to complex problems, but training them with reinforcement learning typically requires verifiable rewards that are expensive to create and not possible for all domains. We demonstrate that LLMs…
Hallucinations in multimodal large language models (MLLMs) -- where the model generates content inconsistent with the input image -- pose significant risks in real-world applications, from misinformation in visual question answering to…
Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier…
Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (MCQs) offer a scalable source of verifiable data but risk…