mlsanityData to 14 Oct 2026

GIFT: Guided Importance-Aware Fine-Tuning for Diffusion Language Models

arXiv 2509.20863 ↗First posted 25 Sep 2025cs.CLcited by 4

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains challenging, as they lack precise probability estimates at each denoising step. While the diffusion mechanism enables the model to reason over entire sequences, it also makes the generation process less predictable and often inconsistent. This highlights the importance of controlling key tokens that guide the direction of generation. To address this issue, we propose GIFT, an importance-aware finetuning method for diffusion language models, where tokens are assigned different importance weights based on their entropy. Derived from diffusion theory, GIFT delivers substantial gains: across diverse settings including different mainstream training datasets ranging from 1k to 10k in size, utilizing LoRA or full parameter fine-tuning, and training on base or instruct models, GIFT consistently achieves superior overall performance compared to standard SFT on four widely used reasoning benchmarks (Sudoku, Countdown, GSM8K, and MATH-500).

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 18 of its 39 references that are in the map. First posted on arXiv 25 Sep 2025.

Builds on

18 of 39 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Dream 7B: Diffusion Large Language Models21 Aug
  2. 2025wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models7 Jul
  3. 2025Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models15 May
  4. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct

Other references · 14

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  6. 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoningcited by 559
  7. 2025The Entropy Mechanism of Reinforcement Learning for Reasoning Language Modelscited by 485
  8. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 285
  9. 2021Curriculum Learning: A Surveycited by 259
  10. 2025MMaDA: Multimodal Large Diffusion Language Modelscited by 250
  11. 2025d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learningcited by 186
  12. 2024Rho-1: Not All Tokens Are What You Needcited by 133
2 more
  1. 2025On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectificationcited by 127
  2. 2015Variance Reduction in SGD by Distributed Importance Samplingcited by 79

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Learnability-Informed Fine-Tuning of Diffusion Language Modelscited by 3
  2. 2026Supervised Fine-Tuning Needs to Unlock the Potential of Token Prioritycited by 0
  3. 2026Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Modelscited by 0
  4. 2026Fine-Tuning Diffusion Language Models with Context Selection and Target Weightingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Large Language Models to Diffusion Finetuning
  2. 2026Diffusion Language Models: An Experimental Analysis
  3. 2026Generative Frontiers: Why Evaluation Matters for Diffusion Language Models
  4. 2023Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
  5. 2026Scaling Beyond Masked Diffusion Language Models
  6. 2023Likelihood-Based Diffusion Language Models
  7. 2026Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models
  8. 2023A Closer Look at Parameter-Efficient Tuning in Diffusion Models