d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning

• URL: http://arxiv.org/abs/2504.12216v1
• Date: Wed, 16 Apr 2025 16:08:45 GMT
• Title: d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
• Authors: Siyan Zhao, Devaansh Gupta, Qinqing Zheng, Aditya Grover,
• Abstract summary: Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL)<n>We propose d1, a framework to adapt pre-trained dLLMs into reasoning models via a combination of supervised finetuning (SFT) and RL.<n>We find that d1 yields the best performance and significantly improves performance of a state-of-the-art dLLM.
• Score: 31.531278643184656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL). These capabilities have primarily been demonstrated within the left-to-right autoregressive (AR) generation paradigm. In contrast, non-autoregressive paradigms based on diffusion generate text in a coarse-to-fine manner. Although recent diffusion-based large language models (dLLMs) have achieved competitive language modeling performance compared to their AR counterparts, it remains unclear if dLLMs can also leverage recent advances in LLM reasoning. To this end, we propose d1, a framework to adapt pre-trained masked dLLMs into reasoning models via a combination of supervised finetuning (SFT) and RL. Specifically, we develop and extend techniques to improve reasoning in pretrained dLLMs: (a) we utilize a masked SFT technique to distill knowledge and instill self-improvement behavior directly from existing datasets, and (b) we introduce a novel critic-free, policy-gradient based RL algorithm called diffu-GRPO. Through empirical studies, we investigate the performance of different post-training recipes on multiple mathematical and logical reasoning benchmarks. We find that d1 yields the best performance and significantly improves performance of a state-of-the-art dLLM.

Related papers

• SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models [39.551767637896404]
  This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs) We show that SFT can significantly undermine subsequent RL by inducing pseudo reasoning paths'' imitated from expert models. We introduce VLAA-Thinking, a new multimodal dataset designed to support reasoning in LVLMs.
  arXiv  Detail & Related papers  (2025-04-10T16:54:05Z)
• Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking [39.48406368755411]
  Large Language Models (LLMs) have introduced Reasoning Large Language Models (RLLMs)<n>RLLMs exhibit innate Chain-of-Thought (CoT) reasoning capability obtained from training, leading to a natural question: "Is CoT prompting necessary to enhance the reasoning capability of RLLMs?"<n>We present the first comprehensive analysis of the impacts of Zero-shot CoT and Few-shot CoT on RLLMs across mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-25T12:37:22Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training [66.48331530995786]
  We propose syMmetry-ENhanceD (MEND) Data Augmentation, a data-centric approach that improves the model's ability to extract useful information from context.<n>Unlike existing methods that emphasize reasoning chain augmentation, our approach improves model robustness at the knowledge extraction stage.<n>Experiments on both logical and arithmetic reasoning tasks show that MEND enhances reasoning performance across diverse query variations.
  arXiv  Detail & Related papers  (2025-02-25T03:03:35Z)
• Large Language Diffusion Models [77.02553707673418]
  Autoregressive models (ARMs) are widely regarded as the cornerstone of large language models (LLMs)<n>We introduce LLaDA, a diffusion model trained from scratch under the pre-training and supervised fine-tuning paradigm.<n>Across extensive benchmarks, LLaDA demonstrates strong scalability, outperforming our self-constructed ARM baselines.
  arXiv  Detail & Related papers  (2025-02-14T08:23:51Z)
• Scalable Language Models with Posterior Inference of Latent Thought Vectors [52.63299874322121]
  Latent-Thought Language Models (LTMs) incorporate explicit latent thought vectors that follow an explicit prior model in latent space.<n>LTMs possess additional scaling dimensions beyond traditional LLMs, yielding a structured design space.<n>LTMs significantly outperform conventional autoregressive models and discrete diffusion models in validation perplexity and zero-shot language modeling.
  arXiv  Detail & Related papers  (2025-02-03T17:50:34Z)
• BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning [78.63421517563056]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. We present a unified probabilistic framework that formalizes LLM reasoning through a novel graphical model. We introduce the Bootstrapping Reinforced Thinking Process (BRiTE) algorithm, which works in two steps.
  arXiv  Detail & Related papers  (2025-01-31T02:39:07Z)
• Scaling Diffusion Language Models via Adaptation from Autoregressive Models [105.70889434492143]
  Diffusion Language Models (DLMs) have emerged as a promising new paradigm for text generative modeling.<n>We show that we can convert AR models ranging from 127M to 7B parameters into diffusion models DiffuGPT and DiffuLLaMA, using less than 200B tokens for training.<n>Our experimental results reveal that these models outperform earlier DLMs and are competitive with their AR counterparts.
  arXiv  Detail & Related papers  (2024-10-23T14:04:22Z)
• Can formal argumentative reasoning enhance LLMs performances? [0.3659498819753633]
  We present a pipeline (MQArgEng) to evaluate the effect of introducing computational argumentation semantics on the performance of Large Language Models (LLMs) Exploratory results indicate that MQArgEng provides a moderate performance gain in most of the examined topical categories and, as such, show promise and warrant further research.
  arXiv  Detail & Related papers  (2024-05-16T22:09:31Z)
• Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models [0.8133739801185272]
  The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) We propose the Self-refine Instruction-tuning method that elicits Smaller Language Models to self-refine their abilities. Results obtained on commonsense and math reasoning tasks show that this approach significantly outperforms Instruction-tuning in both in-domain and out-domain scenarios.
  arXiv  Detail & Related papers  (2024-05-01T09:10:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.