NeurIPS paper: hidden measurement error in LLM pipelines distorts benchmarks
fhuszar · x · 2026-11-18
A new NeurIPS paper, "Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking," argues that evals drive deployment, safety standards, and research, yet the field ignores noise from prompts, judge models, and agent harnesses — systematically underestimating error in benchmarking and annotation, with the problem worsening as data grows. Author Solomon Mg threads through implications for confidence intervals, fixes, and how this makes benchmark hacking easier.
More from Research
- sokrypton shows models can reason about which beta sheets interact — sokrypton · 2026-11-18
- OpenAI study: persona-style CoT training drops monitorability from 0.94 to 0.22 — dair_ai · 2026-11-18
- LLM protein-folding test on fresh PDB entry lands near-random structures — MoAlQuraishi · 2026-11-18
- Lean-PEP turns worst-case optimization bounds into formally verified Lean proofs — prof_grimmer · 2026-11-18
- Two arms, two token streams, one shared vocabulary: new robot manipulation work open-sourced — DJiafei · 2026-11-18
- NUS's BiCAT action tokenizer for bimanual robots: 113/150 real-robot wins, 2.7x lower latency than OAT — DJiafei · 2026-11-18