An energy-based scoring head trained on dense embeddings improves abstention decisions for medical RAG systems on semantically hard out-of-distribution queries compared to softmax and kNN baselines.
In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp
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
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare
An energy-based scoring head trained on dense embeddings improves abstention decisions for medical RAG systems on semantically hard out-of-distribution queries compared to softmax and kNN baselines.