pith. sign in

arxiv: 2510.01384 · v4 · pith:JLTXCAQUnew · submitted 2025-10-01 · 💻 cs.LG

Fine-Tuning Masked Diffusion for Provable Self-Correction

classification 💻 cs.LG
keywords self-correctionmaskedqualityapproachdiffusiongenerativeinferencelow-quality
0
0 comments X
read the original abstract

A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces, their capacity for self-correction remains poorly understood. Prior attempts to incorporate self-correction into MDMs either require overhauling MDM architectures/training or rely on imprecise proxies for token quality, limiting their applicability. Motivated by this, we introduce PRISM--Plug-in Remasking for Inference-time Self-correction of Masked Diffusions--a lightweight, model-agnostic approach that applies to any pretrained MDM. Theoretically, PRISM defines a self-correction loss that provably learns per-token quality scores, without RL or a verifier. These quality scores are computed in the same forward pass with MDM and used to detect low-quality tokens. Empirically, PRISM advances MDM inference across domains and scales: Sudoku; unconditional text (170M); and code with LLaDA (8B).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement

    cs.AI 2026-06 conditional novelty 7.0

    Flow models reach 99.2% Sudoku accuracy in 7 passes and 96.1% on out-of-distribution Sudoku-Extreme by selecting dynamically stable candidates and training with self-conditioning plus DPO to avoid failed outputs.

  2. VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing

    cs.LG 2026-06 unverdicted novelty 7.0

    MDM-VGB augments masked diffusion with backtracking-style reward-guided remasking to achieve quadratic-complexity high-reward generation and sample editing, with proofs of noise robustness.

  3. Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement

    cs.LG 2026-05 unverdicted novelty 7.0

    IPR improves valid solution rates on MNIST Sudoku from 55.8% to 75.0% by iteratively refining partial regions in sequential diffusion models without external verifiers or reward models.

  4. Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models

    cs.CL 2026-04 unverdicted novelty 7.0

    Token-to-Mask remasking improves self-correction in diffusion LLMs by resetting erroneous commitments to masks rather than overwriting them, yielding +13.33 points on AIME 2025 and +8.56 on CMATH.

  5. Locally Coherent Parallel Decoding in Diffusion Language Models

    cs.CL 2026-03 unverdicted novelty 7.0

    CoDiLA adds a compact auxiliary AR model on diffusion latents to enforce local sequential validity during parallel token sampling in discrete diffusion language models.

  6. Discrete Stochastic Localization for Non-autoregressive Generation

    cs.LG 2026-02 unverdicted novelty 7.0

    Discrete Stochastic Localization lets a single trained network support an entire family of per-token SNR paths for discrete sequence generation, with masked diffusion as a special case, and improves MAUVE scores when ...

  7. A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding

    cs.LG 2026-06 unverdicted novelty 6.0

    A2D2 derives the Radon-Nikodym derivative for joint insertion-unmasking paths in discrete diffusion to enable reward-tilted fine-tuning and introduces the Adaptive Joint Decoding loss.

  8. NAVIRA: Decoupled Stochastic Remasking for Masked Diffusion Language Models

    cs.CL 2026-06 unverdicted novelty 6.0

    NAVIRA decouples quality scoring from regeneration via stochastic remasking in masked diffusion LMs, improving fluency and LLM-judge scores on a 170M model.

  9. Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models

    cs.CL 2026-05 unverdicted novelty 6.0

    Presents D3IM sampler and SCOPE post-training that enable visible-token revision in masked diffusion LMs, reporting double-digit gains on GSM8K and HumanEval for LLaDA-8B.

  10. DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs

    cs.CL 2026-05 unverdicted novelty 6.0

    Adapting LLaDA-8B-Instruct via Discrete Stochastic Localization with continuous per-token Gaussian noise yields continuous denoising that achieves top ROUGE-1 on zero-shot summarization at low step budgets and adds se...

  11. Re-evaluating Confidence Remasking in Masked Diffusion Language Models

    cs.LG 2026-06 unverdicted novelty 3.0

    Re-evaluation finds post-hoc remasking (WINO) yields little-to-no gain over confidence unmasking in standard dLLM settings and can worsen diversity collapse under stochastic decoding.