SPD: Single Pass Decoding for Generative Reranking
Quick summary
arXiv:2609.01807v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve state-of-the-art generative ranking quality, but the ranking they produce must be decoded, and autoregressive decoding spends one sequential forward pass per emitted token. We observe that the only tokens a ranker must emit are the $N$ ordinal values naming the items in ranked order, and that this narrow, permutation-structured output format admits decoding strategies which are much more efficient than left-to-right generation. We introduce SPD (Single Forward Pass), a format-specialized decoding str
Key takeaways
- arXiv:2609.01807v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve state-of-the-art generative ranking quality, but the ranking they produce must be decoded, and autoregressive decoding spends one sequential forward pass per emitted token.
- We observe that the only tokens a ranker must emit are the $N$ ordinal values naming the items in ranked order, and that this narrow, permutation-structured output format admits decoding strategies which are much more efficient than left-to-right generation.
- We introduce SPD (Single Forward Pass), a format-specialized decoding str
Why it matters
The importance of “SPD: Single Pass Decoding for Generative Reranking” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments