AOP-Smart RAG framework raises LLM accuracy on AOP question-answering from 15-35% to 95-100% across three models on a 20-task test set.
Survey of hal- lucination in natural language generation.ACM Computing Surveys, 55(12):1–38, March 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AOP-Smart: A RAG-Enhanced Large Language Model Framework for Adverse Outcome Pathway Analysis
AOP-Smart RAG framework raises LLM accuracy on AOP question-answering from 15-35% to 95-100% across three models on a 20-task test set.