Preprint
Aug 2026
Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression
A compact classifier is trained to rank omitted sentences by whether they are needed to interpret retained text and reinsert the top-ranked candidates without support annotations at inference, training a compact classifier to optimize both relevance and referential completeness.
Zheng Hu, Kai Li, Dapeng Fu et al.
· 0 citations