When LLMs Benchmark Themselves: Deconstructing Self-Bias in Automated Evaluation

ArXi:2509.26600v2 Announce Type: replace-cross As LLMs rapidly saturate existing benchmarks, automated benchmark creation using LLMs (LLM-as-a-benchmark) -- where a model generates test inputs (LLM-as-a-testset) and evaluates outputs (LLM-as-an-evaluator) -- has gained traction as a cheap alternative to human curation. We show that this paradigm has a fundamental problem: LLM-generated benchmarks systematically favor the model that created them.