Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage

arXiv:2609.13003 · cs.CL, cs.LG · Submitted 2026-09-11 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-11

Updated: 2026-09-11

Comments: 31 pages, 4 figures. Code and data: https://github.com/foadnamjoo/audit-prune and https://huggingface.co/datasets/foadnamjoo/audit-prune

Code: https://github.com/foadnamjoo/audit-prune

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 3× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering