DiffRetriever uses parallel masked tokens in diffusion LMs for retrieval representations, outperforming DiffEmbed and other baselines on aggregate effectiveness while supporting efficient multi-representation matching.
Improving text embeddings with large language models , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
DiffRetriever uses parallel masked tokens in diffusion LMs for retrieval representations, outperforming DiffEmbed and other baselines on aggregate effectiveness while supporting efficient multi-representation matching.