Research graph
References from The political preferences of LLMs. Local targets link to admitted publications; unresolved targets remain external evidence.
Unresolved reference
External reference
Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor
2019 · External reference
Semantics derived automatically from language corpora contain human-like biases
10.1126/science.aal4230 · 2017 · External reference
Accuracy Comparison Across Face Recognition Algorithms: Where Are We on Measuring Race Bias?
10.1109/tbiom.2020.3027269 · 2021 · External reference
Algorithmic Bias in Recidivism Prediction: A Causal Perspective (Student Abstract)
10.1609/aaai.v34i10.7192 · 2020 · External reference
Fair Is Better than Sensational: Man Is to Doctor as Woman Is to Doctor
10.1162/coli_a_00379 · 2020 · External reference
Wide range screening of algorithmic bias in word embedding models using large sentiment lexicons reveals underreported bias types
10.1371/journal.pone.0231189 · 2020 · External reference
Quantifying and alleviating political bias in language models
10.1016/j.artint.2021.103654 · 2022 · External reference
More human than human: measuring ChatGPT political bias
10.1007/s11127-023-01097-2 · 2024 · External reference
Diminished diversity-of-thought in a standard large language model
2024 · External reference
The Political Biases of ChatGPT
10.3390/socsci12030148 · 2023 · External reference
The Self-Perception and Political Biases of ChatGPT
10.1155/2024/7115633 · 2024 · External reference
The political ideology of conversational AI: Converging evidence on ChatGPT’s pro-environmental, left-libertarian orientation
2023 · External reference
10.18653/v1/2023.acl-long.656
10.18653/v1/2023.acl-long.656 · External reference
Measuring Political Preferences
10.2307/2111702 · 1996 · External reference
Unresolved reference
External reference
OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMs
External reference
Steering LLMs Towards Unbiased Responses: A Causality-Guided Debiasing Framework
External reference
Unresolved reference
External reference
Unresolved reference
External reference
Unresolved reference
External reference
Unresolved reference
External reference
Unresolved reference
External reference
Unresolved reference
External reference
Unresolved reference
External reference
Unresolved reference
External reference
Political Quiz ‐ where do you stand in the Nolan Test?
External reference
Unresolved reference
External reference
Unresolved reference
External reference
LMSys Chatbot Arena Leaderboard ‐ a Hugging Face Space by lmsys
External reference
ChatGPT outperforms crowd workers for text-annotation tasks
10.1073/pnas.2305016120 · 2023 · External reference
Unresolved reference
External reference
DepolarizingGPT ‐ The 3-Answer Political AI from Developmental Politics
External reference
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
External reference
Large Language Models Are Not Robust Multiple Choice Selectors
External reference
