发表机构
Oklahoma State University（俄克拉荷马州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究基于方面的情感分析中的反事实评估难题，提出CAVE-ABSA框架，通过定位观点跨度、可控重写、修复优化、多维度过滤等生成和验证方面级反事实，用于数据集构建及测试模型情感推理能力。
AI 中文摘要
基于方面的情感分析（ABSA）要求模型识别对特定方面的情感，而非依赖句子的全局极性。这使得反事实评估极具挑战性：有效的反事实应翻转一个目标方面的情感，同时保留所有非目标方面的情感、语义含义、流畅性和事实一致性。现有反事实生成方法常聚焦句子级标签翻转且可能产生方面无效、语义漂移或矛盾的编辑。为解决此局限，我们提出CAVE-ABSA，一个用于生成和验证方面级反事实的约束感知验证编辑框架。CAVE-ABSA定位与目标方面相关的观点跨度，进行可控的反事实重写，通过修复模块优化候选，并使用方面级验证、语义相似性、AMR引导的结构保留、编辑最小化、流畅性和矛盾检测进行过滤。该框架旨在构建用于鲁棒性评估和数据增强且经过验证的反事实ABSA数据集。通过明确分离生成与验证，CAVE-ABSA为生成有意义的方面局部反事实以及测试ABSA模型是否真正依赖基于方面的情感推理提供了原则性方法。
英文摘要
Aspect-Based Sentiment Analysis (ABSA) requires models to identify sentiment toward specific aspects rather than relying on the global polarity of a sentence. This makes counterfactual evaluation especially challenging: a valid counterfactual should flip the sentiment of one target aspect while preserving the sentiment of all non-target aspects, semantic meaning, fluency, and factual consistency. Existing counterfactual generation methods often focus on sentence-level label flipping and may produce edits that are fluent but aspect-invalid, semantically drifting, or contradictory. To address this limitation, we propose CAVE-ABSA, a Constraint-Aware Validated Editing framework for generating and validating aspect-level counterfactuals. CAVE-ABSA localizes the opinion span associated with the target aspect, performs controlled counterfactual rewriting, refines candidates through a repair module, and filters them using aspect-level verification, semantic similarity, AMR-guided structural preservation, edit minimality, fluency, and contradiction detection. The framework is designed to construct validated counterfactual ABSA datasets for robustness evaluation and data augmentation. By explicitly separating generation from validation, CAVE-ABSA provides a principled approach for producing meaningful aspect-local counterfactuals and for testing whether ABSA models truly rely on aspect-grounded sentiment reasoning.
Comments15 pages, 1 figure, and 5 tables. Accepted for presentation at the 2nd International Workshop on Informing ML with Knowledge Engineering for Hybrid Intelligent Systems (HHAI-KEML 2026), Brussels, Belgium
