DCRF uses zero-shot LLM prompts to pick the best ranking among eight rerankers per query, beating each individual reranker on most datasets and approaching RankGPT-level quality, but the reported scores select the best prompt per dataset from test labels.
- All ratings are between 0-5 where 0 is very poor and 5 is very good
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Distributed Collaborative Retrieval Framework Excelling in All Queries and Corpora based on Zero-shot Rank-Oriented Automatic Evaluation
DCRF uses zero-shot LLM prompts to pick the best ranking among eight rerankers per query, beating each individual reranker on most datasets and approaching RankGPT-level quality, but the reported scores select the best prompt per dataset from test labels.