Learned LLM review checklist cuts ranking error by over half, wins AI-Native Academia award
JessicaHullman · x · 2026-10-30
In simulated review with LLMs on held-out NeurIPS 2021 and ICLR 2022 papers, the learned checklist reduces error by 21–58%, outperforming the official NeurIPS 2021 checklist at every size; in a human study ranking NeurIPS papers it cuts ranking error by more than half. The work, with Zeddd Liu, Ziyang Guo and Jason Hartline, won an award at the NeurIPS AI-Native Academia workshop.
More from Research
- Commonroom beta: chat with neuron-steered LLM personas and hunt emergent personalities — repligate · 2026-10-30
- Elorian launches visual reasoning model Glimpse alongside DecoyCount benchmark — AndrewDai · 2026-10-30
- Instruction Capacity paper quantifies rule-following limits: GPT-4o mini holds ~37 rules at 95% accuracy — Hennadii Kutomanov · 2026-10-30
- Guidelabs launches Causal Diffusion Engine, adding interpretability to diffusion LLMs with no latency cost — juliusadml · 2026-10-30
- Alice & Bob says RSA-2048 falls in 3.14 days with 23,000 cat qubits — jedisct1 · 2026-10-30
- FlexGlue's 0.6 px average keypoint shift matches SIFT's subpixel refinement threshold — ducha_aiki · 2026-10-30