Political bias audits of LLMs largely capture sycophantic accommodation to the inferred political identity of the asker rather than any fixed model ideology.
The political ideology of conver- sational AI: Converging evidence on ChatGPT’s pro-environmental, left-libertarian orientation
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
A new dual-probe method shows LLMs exhibit 2-3 times more sycophancy during argumentative debates than direct questioning, with models often mirroring users under sustained pressure.
LLMs show systematic directional bias favoring intervention-oriented causal judgments over market-oriented ones in ideologically contested economic scenarios.
Conversational AI matches self-directed internet search in increasing belief in true political information and decreasing belief in misinformation.
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
LLMs display political plasticity via prompt-driven ideological adaptation that is more reliable in larger newer models, but inverted questions produce counterintuitive shifts suggesting data leakage.
citing papers explorer
-
Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor
Political bias audits of LLMs largely capture sycophantic accommodation to the inferred political identity of the asker rather than any fixed model ideology.
-
Measuring Opinion Bias and Sycophancy via LLM-based Persuasion
A new dual-probe method shows LLMs exhibit 2-3 times more sycophancy during argumentative debates than direct questioning, with models often mirroring users under sustained pressure.
-
Ideological Bias in LLMs' Economic Causal Reasoning
LLMs show systematic directional bias favoring intervention-oriented causal judgments over market-oriented ones in ideologically contested economic scenarios.
-
Conversational AI increases political knowledge as effectively as self-directed internet search
Conversational AI matches self-directed internet search in increasing belief in true political information and decreasing belief in misinformation.
-
A Roadmap to Pluralistic Alignment
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
-
Political Plasticity: An Analysis of Ideological Adaptability in Large Language Models
LLMs display political plasticity via prompt-driven ideological adaptation that is more reliable in larger newer models, but inverted questions produce counterintuitive shifts suggesting data leakage.
- Reducing Political Manipulation with Consistency Training
- Persona-Model Collapse in Emergent Misalignment
- Efficient Preference Poisoning Attack on Offline RLHF