BABE Baseline — RoBERTa Fine-tune Reproduction
Reproducing sentence-level media bias classification on BABE. A clean RoBERTa-base fine-tune that beats published baselines at 0.857 macro-F1.
RoBERTaNLPReproduction
Research
Studies, audits, and reproductions.
MBIB Quality Observatory
An audit of the Media Bias Identification Benchmark — label noise probes, near-duplicate detection, and LLM review across 8 tasks.
BenchmarkingCleanlabLLM Review
Rec-Dating Project
A study of the rec-dating dataset as a role-based bipartite network, separating outgoing rating activity from received attention and applying HITS consistently.
NetworksHITSBipartitePython
Community Notes X Rescue
Full analytical workflow for a paper on rescuing Community Notes stuck in 'Needs More Ratings' through clustering, rescue simulation, topic modeling, and LLM validation.
Community NotesClusteringTopic ModelingLLM