SARDI uses lookahead tokens from low-confidence predictions in discrete diffusion language models to dynamically guide retrieval during denoising, outperforming training-free baselines on five multi-hop QA benchmarks at up to 8x higher throughput.
T hink N ote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Self-Augmenting Retrieval for Diffusion Language Models
SARDI uses lookahead tokens from low-confidence predictions in discrete diffusion language models to dynamically guide retrieval during denoising, outperforming training-free baselines on five multi-hop QA benchmarks at up to 8x higher throughput.