Signals 4 · free daily AI digest

A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring

Paper recorded by Signals 4 on 2026-08-28 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-28 on arXiv · recorded by Signals 4 on 2026-08-31

Category: cs.CL · 自然语言处理 · first seen 2026-08-31

Abstract

Multi-trait Automated Essay Scoring (AES) requires rubric-grounded reasoning across interdependent traits, rather than isolated score prediction. Existing feedback-enhanced methods often decouple feedback from scoring or assess traits independently, weakening score--feedback consistency and rubric alignment. We propose HiFTS, a unified autoregressive framework that generates hierarchical CoT feedb

Read on arXiv →

#179 most recent of 186 cs.CL papers we have recorded · ↑ newer: Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Ana · ↓ older: CultureConverse: A Multilingual Multi-turn Simulation Harness for Cult
Cite this page: A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring: the #179 most recent of 186 cs.CL papers we have recorded (as of 2026-08-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/a-unified-framework-to-elicit-structured-feedback-for-interpretable-multi-trait-.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions