AutoRAG-LoRA reports a 46.6% relative reduction in classifier-flagged hallucinations on TruthfulQA, but the evaluation uses the same classifier that triggers the corrective training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
AutoRAG-LoRA: Hallucination-Triggered Knowledge Retuning via Lightweight Adapters
AutoRAG-LoRA reports a 46.6% relative reduction in classifier-flagged hallucinations on TruthfulQA, but the evaluation uses the same classifier that triggers the corrective training.