AL4RAG uses a retrieval-aware similarity metric to select annotation-worthy RAG conversation records, yielding DPO-trained models that reject hallucination-prone queries and preserve answer quality.
Active learning principles for in-context learning with large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables
AL4RAG uses a retrieval-aware similarity metric to select annotation-worthy RAG conversation records, yielding DPO-trained models that reject hallucination-prone queries and preserve answer quality.