arXiv cs.CL· Shima Esfandyari, Seywan Soleymanbaigi, Fardin Akhlaghian Tab, Fatemeh Daneshfar, Mourad Oussalah·· 12 小时前AI 评分20
DRIFT：用依存句法树增强 LLM 的方面情感四元组预测
Dependency Reasoning for Aspect Sentiment Quadruple Prediction
AI 导读
DRIFT 将依存句法树线性化后直接注入 LLM 提示词，作为显式关系上下文，让模型基于方面-观点依存关系推理而非仅靠 token 邻近性。
正文 · 原文
Abstract:Aspect Sentiment Quadruple Prediction (ASQP) is fundamentally a relational reasoning problem: identifying aspect-opinion-category-sentiment quadruples requires modeling structured dependencies, not merely sequential co-occurrence. Existing LLM-based approaches incorporate syntactic information indirectly, via retrieval-based demonstration selection or multi-stage training, rather than as unified, single-pass generation-time context. We present DRIFT, which linearizes dependency parse trees and injects them directly into LLM prompts as explicit relational context, enabling the model to reason over aspect-opinion dependencies rather than infer them from token proximity alone. DRIFT further integrates retrieval-augmented in-context learning and a syntax-aware LLM-based adjudication mechanism that complements exact-match evaluation under span-boundary variation. On SemEval Rest15, Rest16, and ACOS, DRIFT achieves the strongest performance among compared generative ASQP methods, reaching 54.47% and 64.10% F1 on Rest15 and Rest16, with consistent gains across short- and medium-distance aspect-opinion configurations; adjudication further shows exact-match metrics systematically underestimate semantically correct predictions.
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.14873 [cs.CL] |
| (or arXiv:2610.14873v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14873 arXiv-issued DOI via DataCite |
Submission history
From: Shima Esfandyari [view email]
[v1]
Sat, 10 Oct 2026 12:46:33 UTC (251 KB)
[v2]
Fri, 16 Oct 2026 12:03:17 UTC (251 KB)
来源：arXiv cs.CL · arxiv.org