Self-Augmenting Retrieval for Diffusion Language Models
- Published
- Source
- arXiv
- Paper number
- 334
- Field
- LLMs / NLP
- arXiv ID
- 2606.06474
Key points
- It uses low-confidence tokens discarded during denoising as a lookahead signal for retrieval.
- It is training-free, retriever-agnostic, and applicable to all discrete diffusion language models.
- It exploits the fact that low-confidence tokens surface key entities before the output is complete.
- It outperforms existing baselines on five multi-hop QA benchmarks.
- It achieves up to 8x higher throughput than prior methods.
Paper links
External research summaries. These are not HDATF publications or measured product results.