Preprint
Source Expertise, Argument Strength, and Multidimensional Source Sensitivity in Large Language Model Evaluation
Large language models are increasingly used to evaluate arguments, responses, and decisions, yet their judgments may be influenced by contextual information about who produced the content. This study examines how source expertise relevance and argument strength affect LLM evaluation and whether source effects differ across logical quality, credibility, persuasiveness, and agreement. Across four large language…
AI Bias
Large Language Models
LLM Evaluation
Responsible AI
Source Attribution
Source Credibility
DOI:
10.21203/rs.3.rs-11544999/v1
Canonical preprint:
Research Square
· Version 1
