arXiv AI By Tong Sun, Mingyang Ma, Jiayang Yu

STAR-OPD: Structured Aspect-Cascade-Aware On-Policy Reward Distillation for ABSA Quadruple Extraction

Read the original on arXiv AI →

The paper introduces STAR-OPD, a structured aspect‑cascade‑aware on‑policy reward distillation method for aspect‑based sentiment analysis (ABSA) quadruple extraction. It addresses a specific failure mode where distilled models produce structurally invalid target‑aspect bindings, leading to hallucinated targets and corrupted downstream predictions. By training on student rollouts and applying set‑structured rewards that enforce binding consistency, target grounding, and fine‑grained aspect disambiguation, STAR‑OPD outperforms both off‑policy and generic on‑policy baselines on E‑ABSA20K and SemEval‑2014, reducing target hallucination and improving performance on structurally hard cases.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
Jul 7

Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe

arXiv:2605. 03677v2 Announce Type: replace Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model.

By Wenjin Hou, Shangpin Peng, Weinong Wang, Zheng Ruan, Yue Zhang, Zhenglin Zhou, Mingqi Gao, Yifei Chen, Kaiqi Wang, Hongming Yang, Chengquan Zhang, Zhuotao Tian, Han Hu, Yi Yang, Fei Wu, Hehe Fan
arXiv AI
Jun 9

Trajectory-Refined Distillation

arXiv:2606. 08432v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollouts.

By Li Jiang, Haoran Xu, Yichuan Ding, Amy Zhang