Self-Augmenting Retrieval for Diffusion Language Models

• URL: http://arxiv.org/abs/2606.06474v1
• Date: Thu, 04 Jun 2026 17:56:27 GMT
• Title: Self-Augmenting Retrieval for Diffusion Language Models
• Abstract summary: We show that discarded tokens are in fact a useful lookahead signal for retrieval-augmented generation.<n>We exploit this through Self-Augmenting Retrieval for Diffusion Language Models (SARDI)<n>SARDI is training-free, retriever-agnostic, and applicable to any reasoning-capable discrete diffusion language model.
• Score: 22.049744034827242
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discrete diffusion language models generate text by iteratively denoising an entire response in parallel. At each step, they predict tentative tokens for every masked position, committing the confident predictions to the output and discarding the unconfident ones. We show that the discarded tokens are in fact a useful lookahead signal for retrieval-augmented generation: even low-confidence tokens often surface salient entities early in the denoising trajectory, enabling retrieval of stronger evidence before the output is finalized. We exploit this through Self-Augmenting Retrieval for Diffusion Language Models (SARDI), a dynamic RAG framework that uses these lookahead tokens to guide retrieval during denoising. SARDI is training-free, retriever-agnostic, and applicable to any reasoning-capable discrete diffusion language model. Across five multi-hop QA benchmarks, SARDI outperforms current training-free diffusion and autoregressive retrieval baselines at up to $8\times$ higher throughput.

Related papers

• AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling [60.04959047453115]
  AURORA-LM is a continuous-latent language model that separates the construction of a decodable text representation from the modeling of its distribution.<n>AURORA-LM achieves the strongest performance among evaluated continuous and diffusion-based language models on OpenWebText free generation and XSum summarization.
  arXiv  Detail & Related papers  (2026-08-03T17:59:50Z)
• Large Language Models Explore by Latent Distilling [17.44180253276711]
  ESamp is a decoding approach that explicitly encourages semantic diversity during generation.<n> ESamp achieves robust generalization across mathematics, science, and code generation benchmarks.
  arXiv  Detail & Related papers  (2026-04-27T19:08:13Z)
• Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models [54.16797570104461]
  Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models.<n>We investigate non-autoregressive decoding in dLLMs by systematically analyzing its inference dynamics along the temporal axis.
  arXiv  Detail & Related papers  (2026-04-12T10:26:41Z)
• DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention [2.7422645382944935]
  We present DyLLM, a training-free inference framework that accelerates decoding by selectively computing only salient tokens.<n>Across diverse reasoning and code-generation benchmarks, DyLLM achieves up to 9.6x higher throughput.
  arXiv  Detail & Related papers  (2026-03-09T07:02:01Z)
• SJD-PV: Speculative Jacobi Decoding with Phrase Verification for Autoregressive Image Generation [20.808533388639468]
  Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency.<n>We introduce a novel training-free acceleration framework that performs phrase-level speculative verification.<n>Our method significantly reduces the number of function evaluations and achieves up to 30% faster decoding without compromising visual fidelity.
  arXiv  Detail & Related papers  (2026-03-02T13:09:15Z)
• Just on Time: Token-Level Early Stopping for Diffusion Language Models [0.0]
  Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient.<n>We introduce a training-free, token-level early stopping approach that identifies convergence independently at each position.<n>This yields adaptive per-token freezing without task-specific fine-tuning, substantially reducing the total number of diffusion steps required.
  arXiv  Detail & Related papers  (2026-02-11T18:44:04Z)
• TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphs [30.313604786976715]
  Diffusion language models (D-LLMs) offer parallel denoising and bidirectional context.<n> hallucination detection for D-LLMs remains underexplored.<n>We introduce TDGNet, a temporal dynamic graph framework that formulates hallucination detection as learning over evolving token-level attention graphs.
  arXiv  Detail & Related papers  (2026-02-08T16:35:30Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation [138.98095392584693]
  We introduce Auto-Regressive Diffusion (AR-Diffusion) to account for the inherent sequential characteristic of natural language. AR-Diffusion ensures that the generation of tokens on the right depends on the generated ones on the left, a mechanism achieved through employing a dynamic number of denoising steps. In a series of experiments on various text generation tasks, AR-Diffusion clearly demonstrated its superiority over existing diffusion language models.
  arXiv  Detail & Related papers  (2023-05-16T15:10:22Z)
• GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator [114.8954615026781]
  We propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator. GanLM is trained with two pre-training objectives: replaced token detection and replaced token denoising. Experiments in language generation benchmarks show that GanLM with the powerful language understanding capability outperforms various strong pre-trained language models.
  arXiv  Detail & Related papers  (2022-12-20T12:51:11Z)
• Instance Regularization for Discriminative Language Model Pre-training [108.41891836796366]
  This work proposes to estimate the complexity of restoring the original sentences from corrupted ones in language model pre-training. Experimental results on natural language understanding and reading comprehension benchmarks show that our approach improves pre-training efficiency, effectiveness, and robustness.
  arXiv  Detail & Related papers  (2022-10-11T14:16:37Z)

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.