A retrieval-augmented generation system using BGE-M3 and a reranker improves LLM accuracy on Chinese QA benchmarks, especially for finance and law questions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Knowledge Retrieval Based on Generative AI
A retrieval-augmented generation system using BGE-M3 and a reranker improves LLM accuracy on Chinese QA benchmarks, especially for finance and law questions.