Jul 2026
ReliableTableQA:How Much Supervision Does Reliability Annotation Need?
This work introduces ReliableTableQA, a framework for training an LLM to annotate the statistical reliability of tabular QA results, and reframe reliability annotation as a data-efficiency problem and delineate precisely when reinforcement fine-tuning does and does not pay off.
Huei-Chung Hu, Hsin-Tai Wu, Koyo Kobayashi
· arXiv.org · 0 citations