From Data to Model in Bias: A Statistical Analysis of Political Bias in the C4 Corpus and Its Impact on LLMs.

@inproceedings{you-2026-data, author = {Jaebeom You and Jaewon Lee and Sehun Lee and Hyuk-Yoon Kwon}, title = {{From Data to Model in Bias: A Statistical Analysis of Political Bias in the C4 Corpus and Its Impact on LLMs}}, booktitle = {{Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining, WSDM 2026, Boise, ID, USA, February 22-26, 2026}}, pages = {860--870}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3773966.3777990}, doi = {https://doi.org/10.1145/3773966.3777990} }