← Browse all papers
Research domain
Bias & Epistemic Risk
The Bias & Epistemic Risk domain comprises 525 papers in this corpus published between 2004 and 2026. Work here is dominated by Conceptual, Empirical Study, Experimental.
Methodology profile
- Conceptual129 (25%)
- Empirical Study90 (17%)
- Experimental76 (14%)
- Literature Review54 (10%)
- Benchmarking40 (8%)
- Content Analysis37 (7%)
Themes covered
- Epistemic Risk283 (54%)
- Hallucination Control130 (25%)
- Responsible AI Use56 (11%)
- Evaluation & Benchmarks37 (7%)
- Authorship & Attribution1 (0%)
Frequent sub-topics
LLM personality, language ideology propagation, and societal bias · 1moral consistency in LLM decision-making under prompt perturbations · 1exploratory machine learning models in scientific practice · 1AI hallucination and epistemic authority in information systems · 1algorithmic bias in AI-based clinical decision systems · 1judgment-embedded AI outputs and professional decision-making · 1AI-generated image detection and authenticity judgment · 1structural biases in LLM-as-a-Judge systems · 1
Representative papers
- Detecting hallucinations in large language models using semantic entropySebastian Farquhar · 2024 · 621 citations
- Bias in Large Language Models: Origin, Evaluation, and MitigationYufei Guo · 2026 · 20 citations
- Hallucination, monofacts, and miscalibration: An empirical investigationMiranda Muqing Miao · 2026 · 2 citations
- Machine Learning Discoveries and Scientific Understanding in Particle Physics: Problems and Prospects2025 · 1 citations
- Bias and Fairness in Large Language Models: A SurveyIsabel O. Gallegos · 2024 · 506 citations
- Situating methods in the magic of Big Data and AIMadeleine Clare Elish · 2017 · 400 citations
- Gender bias and stereotypes in Large Language ModelsHadas Kotek · 2023 · 328 citations
- The Values Encoded in Machine Learning ResearchAbeba Birhane · 2022 · 275 citations