Navigating the ocean of biases : political bias attribution in language models via causal structures

Jenny, David F.; Billeter, Yann; Sachan, Mrinmaya; Schölkopf, Bernhard; Jin, Zhijing

doi:10.48550/arXiv.2311.08605

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-30246

Publication type:	Working paper – expertise – study
Title:	Navigating the ocean of biases : political bias attribution in language models via causal structures
Authors:	Jenny, David F. Billeter, Yann Sachan, Mrinmaya Schölkopf, Bernhard Jin, Zhijing
et. al:	No
DOI:	10.48550/arXiv.2311.08605 10.21256/zhaw-30246
Extent:	27
Issue Date:	15-Nov-2023
Publisher / Ed. Institution:	arXiv
Language:	English
Subjects:	Computation and language; Artificial intelligence; Social network; Information network; Large language model
Subject (DDC):	006: Special computer methods
Abstract:	The rapid advancement of Large Language Models (LLMs) has sparked intense debate regarding their ability to perceive and interpret complex socio-political landscapes. In this study, we undertake an exploration of decision-making processes and inherent biases within LLMs, exemplified by ChatGPT, specifically contextualizing our analysis within political debates. We aim not to critique or validate LLMs' values, but rather to discern how they interpret and adjudicate "good arguments." By applying Activity Dependency Networks (ADNs), we extract the LLMs' implicit criteria for such assessments and illustrate how normative values influence these perceptions. We discuss the consequences of our findings for human-AI alignment and bias mitigation.
URI:	https://digitalcollection.zhaw.ch/handle/11475/30246
Related research data:	https://github.com/david-jenny/LLM-Political-Study
License (according to publishing contract):	CC BY 4.0: Attribution 4.0 International
Departement:	School of Engineering
Organisational Unit:	Centre for Artificial Intelligence (CAI)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2023_Jenny-etal_Political-bias-attribution-in-language-models.pdf		3.17 MB	Adobe PDF	View/Open

Show full item record

Jenny, D. F., Billeter, Y., Sachan, M., Schölkopf, B., & Jin, Z. (2023). Navigating the ocean of biases : political bias attribution in language models via causal structures. arXiv. https://doi.org/10.48550/arXiv.2311.08605

Jenny, D.F. et al. (2023) Navigating the ocean of biases : political bias attribution in language models via causal structures. arXiv. Available at: https://doi.org/10.48550/arXiv.2311.08605.

D. F. Jenny, Y. Billeter, M. Sachan, B. Schölkopf, and Z. Jin, “Navigating the ocean of biases : political bias attribution in language models via causal structures,” arXiv, Nov. 2023. doi: 10.48550/arXiv.2311.08605.

JENNY, David F., Yann BILLETER, Mrinmaya SACHAN, Bernhard SCHÖLKOPF und Zhijing JIN, 2023. Navigating the ocean of biases : political bias attribution in language models via causal structures. arXiv

Jenny, David F., Yann Billeter, Mrinmaya Sachan, Bernhard Schölkopf, and Zhijing Jin. 2023. “Navigating the Ocean of Biases : Political Bias Attribution in Language Models via Causal Structures.” arXiv. https://doi.org/10.48550/arXiv.2311.08605.

Jenny, David F., et al. Navigating the Ocean of Biases : Political Bias Attribution in Language Models via Causal Structures. arXiv, 15 Nov. 2023, https://doi.org/10.48550/arXiv.2311.08605.