BRMGR independently reranks retrieved and LLM-generated passages with zero-shot likelihood scores and combines them by greedy matching, giving small exact match gains on open-domain QA.
Generate rather than retrieve: Large language models are strong context generators,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation
BRMGR independently reranks retrieved and LLM-generated passages with zero-shot likelihood scores and combines them by greedy matching, giving small exact match gains on open-domain QA.