AI & ML
Deal With It: On Better Schedules for Listwise Reranking
arXiv cs.IR0 views
arXiv:2611.22392v1 Announce Type: new Abstract: Listwise LLM rerankers cannot reliably rank hundreds of documents in a single call, and rely on schedules to orchestrate their calls. Parallel schedules split candidates into groups and advance a fixed quota from each. When a group holds more of the top passages than its quota, some are cut, and expensive repair calls become required. We show that the way candidates are split matters where such a quota can bind, and that, in expected cuts, the best split there deals them round-robin by retriever rank, like cards. Although not conceptually new, dealing has remained unanalyzed. We prove that, under a simple retriever model, no split with equal quotas cuts fewer of the true top ten on average, and that contiguous chunks cut more as the retriever improves. DealRank, the simplest schedule our analysis allows, is on average within 0.1 nDCG@10 points of the best schedules over six LLMs, in two rounds. It is consistently 1.1 to 1.4 times faster than BlitzRank with concurrent first calls up to a thousand candidates. There, it needs three rounds and is eleven times faster than the sliding window. In existing schedules such as BlitzRank, dealing reduces repair calls from 59% of queries to 14%, improving latency with no significant change in quality. Random partitioning appears equivalent at a quota of four, as predicted, but ties results to the seed and trails by 1.3 nDCG@10 points at a quota of one over a dense retriever.
Source:https://arxiv.org/abs/2611.22392PreviousNONSENSE: Non-Semantic Strings Expose Semanticity Gaps in Dense RetrievalNextMore Than a Score: Reinforcement Learning with Verbalized Feedback for Generative Recommendation
Related posts
How OpenAI scales PostgreSQL to 800 million users
0dev.to Database
Spec-Driven PBT: Deriving Semantic Invariants from Code Specifications for Agentic Property-based Testing
0arXiv cs.SE
A Grey Literature Review of Graduate Students' Research Practices and Skills in the LLM Era
0arXiv cs.SE
ReBoT-MiCS: Reliability-Aware Bounding Time for Enhancing Timing Behavior of Embedded Mixed-Criticality Systems
0arXiv cs.SE
VoxelSBFL: Voxel-Level Spectrum-Based Failure Prediction for Vision-Language-Action Models
0arXiv cs.SE
Discontinuity-Aware Solvers for Vapor-Compression Cycles
0arXiv cs.NA