Generating Semantically Valid Adversarial Questions for TableQA
원문 초록
Adversarial attack on question answering systems over tabular data (TableQA) can help evaluate to what extent they can understand natural language questions and reason with tables. However, generating natural language adversarial questions is difficult, because even a single character swap could lead to huge semantic difference in human perception. In this paper, we propose SAGE (Semantically valid Adversarial GEnerator), a Wasserstein sequence-to-sequence model for TableQA white-box attack. To preserve meaning of original questions, we apply minimum risk training with SIMILE and entity delexicalization. We use Gumbel-Softmax to incorporate adversarial loss for end-to-end training. Our experiments show that SAGE outperforms existing local attack models on semantic validity and fluency while achieving a good attack success rate. Finally, we demonstrate that adversarial training with SAGE augmented data can improve performance and robustness of TableQA systems.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Interpretable Natural Language Segmentation Based on Link Grammar
From Roots to Rewards: Dynamic Tree Reasoning with RL
Describe Anything Model for Visual Question Answering on Text-rich Images
Warehouse Spatial Question Answering with LLM Agent
VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models
Identifying the Smallest Adversarial Load Perturbations that Render DC-OPF Infeasible
토론
이 논문과 연결된 포럼 글이 아직 없습니다.