arXiv · 2611.13797
Auditing LLM Pseudo-Label Distillation for Review Informativeness at E-Commerce Scale
Abstract
We study hard-label distillation from Gemini 3.1 Flash-Lite to compact encoders on 5.34 million Turkish marketplace reviews. A strict new-SKU temporal test measures teacher fidelity; a separate, teacher-label-blind audit by one company annotator measures editorial agreement. An H3 category prefix slightly improves teacher fidelity on the full new-SKU test. On the 16,000-review chronological audit subset, it instead reduces agreement with both Gemini and the annotator, with a clearer paired difference for CORN than for cross entropy. Thus the context effect depends on the evaluation population, and teacher fidelity alone does not establish editorial alignment. Under the measured offline configurations, a single-L4 student pipeline processes reviews 50.2 times faster than the teacher pipeline.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
M. Emin Dogan, Cansu Er, Aysenur Kulunk, M. Furkan Eseoglu, H. Bahadir Sahin. 2026-11-10. Auditing LLM Pseudo-Label Distillation for Review Informativeness at E-Commerce Scale. https://searcharxiv.com/abs/2611.13797
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.