GLASS preprint teaser: graph-led LLM-assisted scoring of open-ended responses without human coding
GolinoHudson · x · 2026-11-07
The author teases GLASS (Graph-Led, LLM-Assisted Structure and Scoring), a method to discover and score strategies in open-ended responses without human coding.
The accompanying figure shows discovered sentence communities aligning well with human-labeled categories: e.g., an "AI practice quizzing" community (121 sentences) matches the human practice category at φ=.87, and "concept clarification explanations" (86 sentences) matches explanation at φ=.87, while irrelevant communities are dropped.
More from Research
- Unverified claims: frontier labs allegedly gaming ICLR reviews with malicious reviews — examachine · 2026-11-07
- SSF teaches robots to reason about likely hiding spots when searching for hidden objects — _krishna_murthy · 2026-11-07
- 'Die getting Schmidhubered or live long enough to become one': scaling law priority drama — teortaxesTex · 2026-11-07
- Stanford and Together AI propose Next-Concept Modeling to replace next-token prediction — bendee983 · 2026-11-07
- New benchmark shows some LLMs refuse over 50% of legitimate biology queries — nlarusstone · 2026-11-07
- From AI-designed phage DNA to patient care: the ecosystem behind the model — exnx · 2026-11-07