SOURCE-LINKED INTELLIGENCE

Calibrating Small Language Models for Claim Check-Worthiness Detection

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Assessing claim check-worthiness is an essential first step in automated fact-checking pipelines. This work is motivated by a real deployment challenge at an early-stage startup: running large language models (LLMs) over every incoming claim is cost- and latency-prohibitive, yet smaller models sacrifice accuracy. We propose NN-PPI, a pointwise extension of Prediction-Powered Inference (PPI) that calibrates model predictions at inference time as a lightweight post-hoc layer, without re-training the underlying model. NN-PPI achieves weighted F1 gains ranging from 12% to 33.80% depending on the s

Read original source ↗ Open in workspace

recordType

paper

region

Global