Explaining and Improving Model Behavior with k Nearest Neighbor Representations
원문 초록
Interpretability techniques in NLP have mainly focused on understanding individual predictions using attention visualization or gradient-based saliency maps over tokens. We propose using k nearest neighbor (kNN) representations to identify training examples responsible for a model's predictions and obtain a corpus-level understanding of the model's behavior. Apart from interpretability, we show that kNN representations are effective at uncovering learned spurious associations, identifying mislabeled examples, and improving the fine-tuned model's performance. We focus on Natural Language Inference (NLI) as a case study and experiment with multiple datasets. Our method deploys backoff to kNN for BERT and RoBERTa on examples with low model confidence without any update to the model parameters. Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification
Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models
A MISMATCHED Benchmark for Scientific Natural Language Inference
Drop Dropout on Single-Epoch Language Model Pretraining
LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference
Learning to Reason via Mixture-of-Thought for Logical Reasoning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.