Learning peer-review checklists: a pipeline from atomic claims to checklist trees
JessicaHullman · x · 2026-10-30
Jessica Hullman's team presents a pipeline for learning review checklists: extract atomic review claims from historical reviews, filter to claims resolvable from the paper itself, strip/embed/merge claims, build a tree of checklists at varying granularity, and choose the cut maximizing correlated agreement. Historical review datasets can't reveal reviewer behavior under different checklists, so they optimize this proxy — shown under some conditions to approach the MSE-optimal checklist.
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