Skip to content
conftrace_

training instance

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

query access (1) class label (1) long-tail theory (1) unlearning (1) in-context unlearning (1) neuron attribution (1) instance attribution (1) large language model (1) nlp task (1) faithfulness test (1)

Papers

In-Context Unlearning: Language Models as Few-Shot Unlearners ICML 2024 Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods ACL 2024 Characterizing the Impacts of Instances on Robustness ACL 2023 An Empirical Study of Memorization in NLP ACL 2022 Influence Functions for Sequence Tagging Models EMNLP 2022