Beyond AI Detectors: Using infini-gram to Trace LLM Text Origins
allen_ai · x · 2026-08-01
Traditional AI writing detectors only provide a likelihood score without showing whether specific expressions already exist in sources. Allen AI highlighted research by Tuhin Chakrabarti's group at Stony Brook using the infini-gram engine, which indexes massive public text datasets to count phrase occurrences.
The team applied this to books, filtering for rare phrases (appearing in 5 or fewer Google Books and unindexed on the web) to distinguish unique phrasing from clichés. They also analyzed the GrantaGate controversy, finding that text flagged as machine-written heavily matched existing content from fan fiction sites.
Related event: Ai2's infini-gram Engine Tracks AI Plagiarism Traces(9 posts)→
More from Research
- Transforming quadruped robot runs on real hardware: per-pose RL policies in Isaac switched on morph — _Stocko_ · 2026-10-16
- KinoGen synthesizes robot loco-manipulation reference motions directly via kinematically grounded video generation — ChongZzZhang · 2026-10-16
- Science Robotics paper introduces F³, predictive event-based vision beyond optical flow — CSProfKGD · 2026-10-16
- VideoGen-Agent: An 8B Multimodal Agent Turns Video Generation Into a Tool-Use Loop — jiqizhixin · 2026-10-16
- Comprehension Audits: New Paper Proposes a Gate for AI-Written Code at Frontier Labs — ronbodkin · 2026-10-16
- Not Boring #215: Cammarata's Clean Networks Claim, Tesla's Flying Roadster, Tau Cut 73% — Not Boring (Packy McCormick) · 2026-10-16