llm-annotation

LabelHub: AI-assisted data labeling and review platform.

Assessing the reliability of LLM annotations in the context of demographic bias and model explanation (GeBNLP @ ACL 2025)

Auditable appraisal-to-emotion annotation pipeline with evidence tracing, schema validation, and deterministic emotion mapping.

My internship annotation loop to analyze a set of horror fiction novels (including ~60 Stephen King novels and ~50 canonical horror novels, with works by H.P. Lovecraft, Ann Radcliffe and Edgar Allan Poe)

六家主流 AI 助手英语用户评论的跨产品口碑与诉求挖掘 | Cross-product sentiment and demand mining from English user reviews of six major AI assistants

NLP research project on contemporary romantic fiction, combining BERTopic, OCTIS, and Goodreads ratings to model which themes drive higher book scores.

Materials for the paper "Large Language Models Can Extract Metadata for Annotation of Human Neuroimaging Publications"

A dataset-auditing pipeline that flags and reviews label-quality issues across three sentiment classification datasets: the human-annotated SST-2 benchmark, and two LLM-generated synthetic datasets

Reproducible R workflow for LLM-assisted Economic Threat and Economic Benefit annotation in German immigration news.