Fine-tuned GPT ideology labels exhibit significant community-level sentiment-to-ideology causal effects and direct mediation paths that expert human labels lack, consistent with shortcut learning.
Neural Media Bias Detection Using Distant Supervision With BABE - Bias Annotations By Experts
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
UnBias-Plus is an open-source toolkit unifying segment-level multi-class bias classification, biased span localization, neutral text rewriting, and decision reasoning.
citing papers explorer
-
Does Topic Sentiment Cause Perceived Ideology? Comparing Human and LLM Annotations in Political News Articles
Fine-tuned GPT ideology labels exhibit significant community-level sentiment-to-ideology causal effects and direct mediation paths that expert human labels lack, consistent with shortcut learning.
-
UnBias-Plus: Detect, Explain, and Rewrite Bias
UnBias-Plus is an open-source toolkit unifying segment-level multi-class bias classification, biased span localization, neutral text rewriting, and decision reasoning.