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

arXiv: https://arxiv.org/abs/2608.20831 · HTML: https://mlsanity.com/paper/2608.20831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal distillation, one of 12 directions in Knowledge distillation.
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 12 of 12)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022)
- [Teaching Small Language Models to Reason](https://mlsanity.com/paper/2212.08410/) (2022)
- [Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation](https://mlsanity.com/paper/2602.12125/) (2026)
- [Entropy-Aware On-Policy Distillation of Language Models](https://mlsanity.com/paper/2603.07079/) (2026)
- [Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1911.01616/) (2019)
- [Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation](https://mlsanity.com/paper/2210.10291/) (2022)
- [InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2302.08624/) (2023)
- [RLKD: Distilling LLMs' Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2505.16142/) (2025)

## Abstract (arXiv)

Aspect-based sentiment analysis (ABSA) quadruple extraction requires jointly predicting target, aspect, opinion, and sentiment over reviews that often contain multiple fine-grained sentiment tuples. While large chain-of-thought (CoT) models perform well on this task, distilling them into smaller deployable models remains difficult. We identify a task-specific failure mode in distilled ABSA extraction: student errors at the target-aspect interface create structurally invalid states, such as broken target-aspect bindings and hallucinated targets, which then corrupt downstream predictions. Conventional off-policy distillation is poorly suited to this setting because it trains only on teacher-generated trajectories and provides little supervision on the student-induced structural states that dominate inference. To address this mismatch, we propose STAR-OPD (STructured Aspect-cascade-aware On-Policy Reward Distillation), which builds on generic on-policy distillation and instantiates it for ABSA quadruple extraction with cascade-aware, set-structured rewards. STAR-OPD trains on student rollouts and applies set-structured rewards that directly target binding consistency, target grounding, and fine-grained aspect disambiguation. Experiments on E-ABSA20K and SemEval-2014 show that STAR-OPD consistently outperforms off-policy and general on-policy baselines, reduces target hallucination, and substantially improves performance on structurally hard cases. With Qwen3-4B, STAR-OPD substantially narrows the student-teacher gap while improving inference efficiency, highlighting the importance of on-policy structural correction for distilled ABSA extraction.