Skip to content
conftrace_

gradient-based interpretability

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

grammatical agreement (1) neural network (1) backpropagation algorithm (1) input gradient (1) attention analysis (1) information flow (1) large vision-language model (1) vision-language model (1) language model (1) gradient flow (1)

Papers

Understanding or Memorizing? A Case Study of German Definite Articles in Language Models ACL 2026 From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks NAACL 2025 Generalizing Backpropagation for Gradient-Based Interpretability ACL 2023 Do Input Gradients Highlight Discriminative Features? NeurIPS 2021