Self-Generated Error Training for Token Editing in Diffusion Language Models

• URL: http://arxiv.org/abs/2606.17175v1
• Date: Mon, 15 Jun 2026 18:13:54 GMT
• Title: Self-Generated Error Training for Token Editing in Diffusion Language Models
• Abstract summary: Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding.<n>We study this training-inference mismatch and propose self-generated T2T.
• Score: 0.6916773850242582
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at inference the editor sees the model's own fluent, high-confidence draft errors instead. We study this training-inference mismatch and propose self-generated T2T, which performs a no-gradient draft pass, fills masked positions with predicted tokens, and supervises recovery in a second pass under these self-generated corruptions. We implement the update as a short LoRA continued-pretraining pass on LLaDA2.1-mini and evaluate on several benchmarks under the official Q-Mode T2T procedure with unchanged inference parameters. The method generally improves accuracy while reducing T2T edit intensity, mitigating failure modes such as final-digit transcription errors after otherwise correct reasoning and excessive self-correction before short factual answers.

Related papers

• TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM [18.69783590125584]
  Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation.<n>They face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality.<n>Existing acceleration methods often gain speed at the cost of accuracy.<n>We propose TAD, a Temporal-Aware trajectory self-Distillation framework.
  arXiv  Detail & Related papers  (2026-05-10T13:38:53Z)
• Remask, Don't Replace: Token-to-Mask Refinement in Masked Diffusion Language Models [0.6916773850242582]
  Masked diffusion language models such as LLaDA2.1 rely on Token-to-Token editing to correct their own generation errors.<n>We propose Token-to-Mask (T2M) remasking, which resets the position to the mask state so that the next denoising step re-predicts it from an in-distribution context.<n>Across 8 benchmarks, T2M improves accuracy on tasks that require exact token-level output.
  arXiv  Detail & Related papers  (2026-04-20T18:43:28Z)
• Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models [0.6916773850242582]
  LLaDA2.1 introduced a Token-to-Token (T2T) editing mechanism that accelerates generation.<n>We propose Token-to-Mask (T2M) remasking, a training-free, drop-in replacement for T2T editing.<n>T2M resets suspected erroneous tokens back to the mask state, allowing the diffusion process to re-predict them under cleaner context.
  arXiv  Detail & Related papers  (2026-04-06T17:39:11Z)
• From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model [72.73512218682187]
  We introduce ReDiff, a refining-enhanced diffusion framework that teaches the model to identify and correct its own errors.<n>Our approach features a two-stage training process: first, we instill a foundational revision capability by training the model to revise synthetic errors; second, we implement a novel online self-correction loop.<n>This mistake-driven learning endows the model with the crucial ability to revisit and refine its already generated output, effectively breaking the error cascade.
  arXiv  Detail & Related papers  (2025-10-22T06:58:55Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Test-Time Adaptation with Binary Feedback [50.20923012663613]
  BiTTA is a novel dual-path optimization framework that balances binary feedback-guided adaptation on uncertain samples with agreement-based self-adaptation on confident predictions.<n> Experiments show BiTTA achieves 13.3%p accuracy improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-05-24T05:24:10Z)
• SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition [116.31926128970585]
  We propose SoftCorrect with a soft error detection mechanism to avoid the limitations of both explicit and implicit error detection. Compared with implicit error detection with CTC loss, SoftCorrect provides explicit signal about which words are incorrect. Experiments on AISHELL-1 and Aidatatang datasets show that SoftCorrect achieves 26.1% and 9.4% CER reduction respectively.
  arXiv  Detail & Related papers  (2022-12-02T09:11:32Z)
• Converge to the Truth: Factual Error Correction via Iterative Constrained Editing [30.740281040892086]
  We propose VENCE, a novel method for factual error correction (FEC) with minimal edits. VENCE formulates the FEC problem as iterative sampling editing actions with respect to a target density function. Experiments on a public dataset show that VENCE improves the well-adopted SARI metric by 5.3 (or a relative improvement of 11.8%) over the previous best distantly-supervised methods.
  arXiv  Detail & Related papers  (2022-11-22T10:03:13Z)
• FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition [92.12910821300034]
  We propose FastCorrect 2, an error correction model that takes multiple ASR candidates as input for better correction accuracy. FastCorrect 2 achieves better performance than the cascaded re-scoring and correction pipeline.
  arXiv  Detail & Related papers  (2021-09-29T13:48:03Z)
• Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction [49.25830718574892]
  We present a new framework named Tail-to-Tail (textbfTtT) non-autoregressive sequence prediction. Considering that most tokens are correct and can be conveyed directly from source to target, and the error positions can be estimated and corrected. Experimental results on standard datasets, especially on the variable-length datasets, demonstrate the effectiveness of TtT in terms of sentence-level Accuracy, Precision, Recall, and F1-Measure.
  arXiv  Detail & Related papers  (2021-06-03T05:56:57Z)
• Neural Machine Translation with Error Correction [40.61399972202611]
  We introduce an error correction mechanism into NMT, which corrects the error information in the previous generated tokens to better predict the next token. Specifically, we introduce two-stream self-attention from XLNet into NMT decoder, where the query stream is used to predict the next token. We leverage scheduled sampling to simulate the prediction errors during training.
  arXiv  Detail & Related papers  (2020-07-21T09:41:07Z)
• Adversarial Transfer Learning for Punctuation Restoration [58.2201356693101]
  Adversarial multi-task learning is introduced to learn task invariant knowledge for punctuation prediction. Experiments are conducted on IWSLT2011 datasets.
  arXiv  Detail & Related papers  (2020-04-01T06:19:56Z)

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.