STAR-OPD: Structured Aspect-Cascade-Aware On-Policy Reward Distillation for ABSA Quadruple Extraction
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Sentiment AnalysisSimilar Papers 제목 키워드 기반
Towards Sustainable Growth: A Multi-Value-Aware Retrieval Framework for E-Commerce Search
New item growth is critical for maintaining a healthy ecosystem in large-scale e-commerce platforms. However, existing systems tend to prioritize presenting users with already popular items, a phenomenon often referred t…
Value predictionHetCAN: A Heterogeneous Graph Cascade Attention Network with Dual-Level Awareness
Heterogeneous graph neural networks(HGNNs) have recently shown impressive capability in modeling heterogeneous graphs that are ubiquitous in real-world applications. Most existing methods for heterogeneous graphs mainly …
AttributeCrunchLLM: Multitask LLMs for Structured Business Reasoning and Outcome Prediction
Predicting the success of start-up companies, defined as achieving an exit through acquisition or IPO, is a critical problem in entrepreneurship and innovation research. Datasets such as Crunchbase provide both structure…
parameter-efficient fine-tuningDecision MakingFunnel-Structured Cascade for Multi-View Face Detection with Alignment-Awareness
Multi-view face detection in open environment is a challenging task due to diverse variations of face appearances and shapes. Most multi-view face detectors depend on multiple models and organize them in parallel, pyrami…
Face AlignmentFace DetectionCascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution
This paper considers an architecture referred to as Cascade Region Proposal Network (Cascade RPN) for improving the region-proposal quality and detection performance by \textit{systematically} addressing the limitation o…
Object DetectionRegion Proposal