# Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models

arXiv: https://arxiv.org/abs/2509.23653 · HTML: https://mlsanity.com/paper/2509.23653/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 45 of its 50 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 30 of 45)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning](https://mlsanity.com/paper/2309.05653/) (2023)
- [A Continuous Time Framework for Discrete Denoising Models](https://mlsanity.com/paper/2205.14987/) (2022)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data](https://mlsanity.com/paper/2406.03736/) (2024)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models](https://mlsanity.com/paper/2505.19223/) (2025)
- [DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning](https://mlsanity.com/paper/2504.11456/) (2025)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [Remasking Discrete Diffusion Models with Inference-Time Scaling](https://mlsanity.com/paper/2503.00307/) (2025)
- [d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning](https://mlsanity.com/paper/2504.12216/) (2025)
- [Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference](https://mlsanity.com/paper/2508.02193/) (2025)
- [A Reparameterized Discrete Diffusion Model for Text Generation](https://mlsanity.com/paper/2302.05737/) (2023)

## Built on by (most cited first, 30 of 37)

- [Fine-Tuning Masked Diffusion for Provable Self-Correction](https://mlsanity.com/paper/2510.01384/) (2025)
- [Learning Unmasking Policies for Diffusion Language Models](https://mlsanity.com/paper/2512.09106/) (2025)
- [Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Way](https://mlsanity.com/paper/2510.24605/) (2025)
- [Learn from Your Mistakes: Self-Correcting Masked Diffusion Models](https://mlsanity.com/paper/2602.11590/) (2026)
- [Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules](https://mlsanity.com/paper/2512.02892/) (2025)
- [CORE: Context-Robust Remasking for Diffusion Language Models](https://mlsanity.com/paper/2602.04096/) (2026)
- [DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking](https://mlsanity.com/paper/2603.01367/) (2026)
- [Guided Star-Shaped Masked Diffusion](https://mlsanity.com/paper/2510.08369/) (2025)
- [Provably adaptive sampling with uniform and remasking discrete diffusion models](https://mlsanity.com/paper/2608.23554/) (2026)
- [Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models](https://mlsanity.com/paper/2602.10953/) (2026)
- [Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models](https://mlsanity.com/paper/2604.05497/) (2026)
- [Training-Free Self-Correction for Multimodal Masked Diffusion Models](https://mlsanity.com/paper/2602.02927/) (2026)
- [Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models](https://mlsanity.com/paper/2604.16565/) (2026)
- [Edit-Based Refinement for Parallel Masked Diffusion Language Models](https://mlsanity.com/paper/2605.09603/) (2026)
- [Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement](https://mlsanity.com/paper/2606.08357/) (2026)
- [Self-Generated Error Training for Token Editing in Diffusion Language Models](https://mlsanity.com/paper/2606.17175/) (2026)
- [Don't Commit Alone: Joint Token Commitment in Diffusion Language Models](https://mlsanity.com/paper/2607.04469/) (2026)
- [BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models](https://mlsanity.com/paper/2601.06428/) (2026)
- [Reversible Diffusion Decoding for Diffusion Language Models](https://mlsanity.com/paper/2602.00150/) (2026)
- [Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Models](https://mlsanity.com/paper/2604.18738/) (2026)
- [The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models](https://mlsanity.com/paper/2605.24697/) (2026)
- [Re-evaluating Confidence Remasking in Masked Diffusion Language Models](https://mlsanity.com/paper/2606.12232/) (2026)
- [Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes](https://mlsanity.com/paper/2607.13188/) (2026)
- [CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models](https://mlsanity.com/paper/2607.24763/) (2026)
- [From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models](https://mlsanity.com/paper/2607.26504/) (2026)
- [Reconsidering Positional Supervision in Masked Diffusion Language Model Training](https://mlsanity.com/paper/2601.22947/) (2026)
- [Controllable Accent Normalization via Discrete Diffusion](https://mlsanity.com/paper/2603.14275/) (2026)
- [Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast](https://mlsanity.com/paper/2605.01373/) (2026)
- [Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models](https://mlsanity.com/paper/2605.26436/) (2026)
- [Adaptive Order Policies for Masked Diffusion](https://mlsanity.com/paper/2606.00295/) (2026)

## Abstract (arXiv)

Mask-based Diffusion Language Models (DLMs) struggle to revise incorrect tokens: once a token is generated, it typically remains fixed. The key challenge is to identify potential errors in the inputs. In this paper, we propose emphunderlineRemasking-underlineenabled underlineDiffusion Language Model (RemeDi, a mask-based DLM that introduces remasking as another fundamental mechanism, enabling more flexible text refinement in diffusion-based text generation. To achieve this, RemeDi jointly predicts token distributions and per-token confidence scores at each step. The confidence scores determine which tokens to be unmasked after the current step, allowing the model to identify tokens with low quality and remask them. These remasked tokens can be resampled with richer context in subsequent steps. We design a remask-aware pipeline to train this ability, including supervised fine-tuning which teaches the model to detect and remask incorrect tokens in addition to predict mask tokens, and reinforcement learning which optimizes full generation trajectories toward higher rewards. Experiments show that RemeDi achieves the state-of-the-art results among open-source DLMs on multiple datasets.