Machine Unlearning for Masked Diffusion Language Models

• URL: http://arxiv.org/abs/2605.18253v1
• Date: Mon, 18 May 2026 11:54:11 GMT
• Title: Machine Unlearning for Masked Diffusion Language Models
• Abstract summary: Masked diffusion language models (MDLMs) generate text by iteratively denoising masked positions in parallel.<n>We propose Masked Diffusion Unlearning (MDU), the first unlearning framework for MDLMs.<n>MDU minimizes a forward KL divergence from the prompt-conditional prediction to a prompt-masked unconditional anchor at every masked response position.
• Score: 14.122398562530032
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models. Unlike autoregressive models, which generate text sequentially, MDLMs generate text by iteratively denoising masked positions in parallel. During fine-tuning, MDLMs learn to recover responses from masked response states conditioned on a prompt, thereby shifting their predictions from a prompt-masked unconditional distribution toward a prompt-conditional distribution. Despite this distinct generative and fine-tuning mechanism, machine unlearning for MDLMs remains largely unexplored. In this paper, we propose Masked Diffusion Unlearning (MDU), the first unlearning framework for MDLMs, by revisiting the process of learning specific knowledge in terms of diffusion. Specifically, MDU minimizes a forward KL divergence from the prompt-conditional prediction to a prompt-masked unconditional anchor at every masked response position, with a temperature scaling parameter to control the privacy-utility trade-off. Our empirical results on standard benchmarks and MDLM backbones show that MDU achieves high unlearning performance compared to existing LLM unlearning methods. Code is available at https://github.com/leegeoru/MDU.

Related papers

• Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment [46.75006425771645]
  Diffusion language models (DLMs) have recently demonstrated capabilities that complement standard autoregressive (AR) models.<n>We ask whether the internal representation geometry learned by next-token prediction can be explicitly preserved during AR-to-DLM conversion.<n>We introduce REPR-ALIGN, a representation alignment objective that adapts a bidirectional masked diffusion model to reuse representations from a pretrained AR model.
  arXiv  Detail & Related papers  (2026-05-07T19:35:48Z)
• Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models [58.946955321428845]
  This work presents self-rewarding sequential Monte Carlo (SMC)<n>Our algorithm stems from the observation that most existing MDLMs rely on a confidence-based sampling strategy.<n>We introduce the trajectory-level confidence as a self-rewarding signal for assigning particle importance weights.
  arXiv  Detail & Related papers  (2026-02-02T09:21:45Z)
• Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow [30.201913054064363]
  Masked Diffusion Language Models promise parallel token generation and arbitrary-order decoding.<n>We characterize MDLM behavior along two dimensions -- parallelism strength and generation order.<n>We evaluate eight mainstream MDLMs on 58 benchmarks spanning knowledge, reasoning, and programming.
  arXiv  Detail & Related papers  (2026-01-22T02:39:36Z)
• PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs [59.78917775399492]
  Multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability.<n>We propose a training-free framework to mitigate this degradation.
  arXiv  Detail & Related papers  (2026-01-12T15:27:51Z)
• Activation Steering for Masked Diffusion Language Models [1.0980666029958932]
  Masked diffusion language models generate text through an iterative denoising process.<n>We present an activation-steering framework for MDLMs that computes layer-wise steering vectors from a single forward pass.<n>Experiments on LLaDA-8B-Instruct demonstrate reliable modulation of high-level attributes.
  arXiv  Detail & Related papers  (2025-12-30T11:10:52Z)
• Reproducing and Dissecting Denoising Language Models for Speech Recognition [31.91567892562116]
  Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR)<n>This paper presents the first independent, large-scale empirical study of DLMs.
  arXiv  Detail & Related papers  (2025-12-15T17:33:22Z)
• WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens [69.97021957331326]
  We propose Noisy Query Tokens, which learn a distributed representation space between the VLM and Diffusion Model via end-to-end optimization.<n>We also introduce a VAE branch with linear projection to recover fine-grained image details.
  arXiv  Detail & Related papers  (2025-12-02T09:02:20Z)
• DLM-One: Diffusion Language Models for One-Step Sequence Generation [63.43422118066493]
  DLM-One is a score-distillation-based framework for one-step sequence generation with continuous diffusion language models.<n>We investigate whether DLM-One can achieve substantial gains in sampling efficiency for language modeling.
  arXiv  Detail & Related papers  (2025-05-30T22:42:23Z)
• Large Language Diffusion Models [93.26422905620008]
  Large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs)<n>We introduce LLaDA, a diffusion model trained from scratch under the pre-training and supervised fine-tuning paradigm.<n>Across extensive benchmarks on general tasks, math, code, and so on, LLaDA demonstrates strong scalability and performs comparably to our self-constructed ARM baselines.
  arXiv  Detail & Related papers  (2025-02-14T08:23:51Z)
• Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code? [51.29970742152668]
  We highlight relying on accuracy-based measurements may lead to an overestimation of models' capabilities. To address these issues, we introduce a technique called SyntaxEval in Syntactic Capabilities.
  arXiv  Detail & Related papers  (2024-01-03T02:44:02Z)
• Mixture of Soft Prompts for Controllable Data Generation [21.84489422361048]
  Mixture of Soft Prompts (MSP) is proposed as a tool for data augmentation rather than direct prediction. Our method achieves state-of-the-art results on three benchmarks when compared against strong baselines.
  arXiv  Detail & Related papers  (2023-03-02T21:13:56Z)

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.