conftrace_

white-box model

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) black-box model (2) representation learning (2) mechanism understanding (1) sparse rate reduction (1) token compression (1) closed-book question answering (1) interpretability analysis (1) propaganda detection (1) jacobian matrix (1)

Papers

Calibrating Large Language Models Using Their Generations Only ACL 2024 White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? JMLR 2024 Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models EMNLP 2023 Rethinking the Construction of Effective Metrics for Understanding the Mechanisms of Pretrained Language Models EMNLP 2023 Adversarial Eigen Attack on Black-Box Models CVPR 2022 ProtoTEx: Explaining Model Decisions with Prototype Tensors ACL 2022 Incremental Learning via Rate Reduction CVPR 2021