analiza aiqbench
This research introduces EssayCBM, a concept bottleneck model that enhances automated essay scoring by decomposing evaluations into eight interpretable writing concepts. Unlike opaque neural language models, this framework provides an auditable mapping from specific concepts to final grades, enabling instructors to inspect and adjust rubric-level predictions in real time while maintaining performance parity with standard baselines.
EssayCBM: Rubric-Aligned Concept Bottleneck Models for Transparent Essay Grading
arXiv:2512.20817v3 Announce Type: replace Abstract: Automated essay scoring (AES) has advanced significantly with neural language models, yet most systems remain opaque, offering little visibility into how grades are produced. In educational settings, instructors must be able to understand, trust, and occasionally override the automated grading decisions. We introduce EssayCBM, a rubric-aligned concept bottleneck framework that decomposes essay evaluation into eight interpretable writing concepts before computing the final score. Unlike direct LLM-based grading approaches, EssayCBM learns an explicit and auditable mapping from writing concepts to grades, allowing instructors to inspect and adjust rubric-level predictions during grading. EssayCBM matches neural AES baselines while making grading decisions transparent and directly editable at the rubric level. We further present an interactive system that demonstrates this capability by allowing instructors to inspect and modify concept predictions in real time.
Abstract:Automated essay scoring (AES) has advanced significantly with neural language models, yet most systems remain opaque, offering little visibility into how grades are produced. In educational settings, instructors must be able to understand, trust, and occasionally override the automated grading decisions. We introduce EssayCBM, a rubric-aligned concept bottleneck framework that decomposes essay evaluation into eight interpretable writing concepts before computing the final score. Unlike direct LLM-based grading approaches, EssayCBM learns an explicit and auditable mapping from writing concepts to grades, allowing instructors to inspect and adjust rubric-level predictions during grading. EssayCBM matches neural AES baselines while making grading decisions transparent and directly editable at the rubric level. We further present an interactive system that demonstrates this capability by allowing instructors to inspect and modify concept predictions in real time.
Computation and Language (cs.CL)
arXiv:2512.20817 [cs.CL]
(or arXiv:2512.20817v3 [cs.CL] for this version)
Text integral sub licența deschisă a publicației · 141 cuvinte
Subiecte conexe
[AINews] High Taste Testers Ep. 1
Latent Space · 17 oct. 2026
Always ask your agent to be honest
LessWrong · 16 sept. 2026
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · 23 sept. 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026