multiPL-e dataset contains hilarious regex errors, generating 'rsthon' tasks
code_star · x · 2026-08-17
Developer codestar highlights a glaring preprocessing error in the multiPL-e dataset's MBPP subset. The dataset attempted to convert Python to Rust code via a simple regex replace (swapping .py for .rs), resulting in absurd instructions to write a 'rsthon' function. Such rudimentary flaws, lingering in benchmark datasets, may have skewed evaluation results for numerous research papers relying on this data.
More from Research
- ImageNet should retire: DiT method rankings negatively correlate between ImageNet and text-to-image — YouJiacheng · 2026-10-16
- GAE paper learns a geometry-native latent space for 3D-consistent world generation — yshan2u · 2026-10-16
- Agents turn conservative as context grows: edits shrink from 150 to 30 lines — dbreunig · 2026-10-16
- LMR-BENCH at EMNLP 2025 tests whether LLM agents can reproduce real LLM research — ZhiyuChen4 · 2026-10-16
- Ex-OpenAI researcher claims most neurons are legible now; critics call it hype — anshulkundaje · 2026-10-16
- Physicist pushes back on ML community's acceptance that models may be beyond understanding — tszzl · 2026-10-16