SOURCE-LINKED INTELLIGENCE
Label-Efficient Document-Grounded Factuality Detection via Cross-Paraphrastic Invariance Learning
Large language models (LLMs) can generate fluent claims that are unsupported by a given source document, motivating accurate and efficient document-grounded factuality detection. Existing LLM-based evaluators often require repeated inference and incur high computational cost, whereas compact factuality detectors are efficient at inference time but commonly rely on large labeled or synthetically generated corpora. We propose CPIL (Cross-Paraphrastic Invariance Learning), a two-stage Siamese framework that converts a small labeled set into relational supervision without acquiring additional fact
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-11-12T04:06:48.000Z
First collected: 2026-11-13T05:52:54.307Z. This is not the publication date.