conftrace_

token-level explanation

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

masking and infilling (1) leave-one-out occlusion (1) cross-architecture comparison (1) top-token flip rate (1) explanation robustness (1) black-box evaluation (1) text detoxification (1) multiple instance learning (1) toxicity detection (1) text generation (1)

Papers

Robust Explanations for User Trust in Enterprise NLP Systems ACL 2026 XDetox: Text Detoxification with Token-Level Toxicity Explanations EMNLP 2024 Generating Token-Level Explanations for Natural Language Inference NAACL 2019