The first integrated taxonomy, empirical study of interplay and shallow dememorization, plus a theoretical guarantee on dememorization depth for certified unlearning.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
years
2026 4representative citing papers
ZK-Value is a practical ZK system for verifiable Shapley-value data valuation using LSH approximations and optimized proofs that matches baseline quality while generating proofs in seconds to minutes.
A unified benchmark of eleven CE methods shows effectiveness-sparsity trade-offs vary by method and format, performance is consistent from item to list level, and graph-based explainers face scalability limits on large graphs.
Data-influence-score filtering using validation-set loss on downstream coding tasks improves Code-LLM performance, with the most beneficial training data varying significantly across different programming tasks.
citing papers explorer
-
SoK: Unlearnability and Unlearning for Model Dememorization
The first integrated taxonomy, empirical study of interplay and shallow dememorization, plus a theoretical guarantee on dememorization depth for certified unlearning.
-
ZK-Value: A Practical Zero-Knowledge System for Verifiable Data Valuation
ZK-Value is a practical ZK system for verifiable Shapley-value data valuation using LSH approximations and optimized proofs that matches baseline quality while generating proofs in seconds to minutes.
-
From Top-1 to Top-K: A Reproducibility Study and Benchmarking of Counterfactual Explanations for Recommender Systems
A unified benchmark of eleven CE methods shows effectiveness-sparsity trade-offs vary by method and format, performance is consistent from item to list level, and graph-based explainers face scalability limits on large graphs.
-
An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models
Data-influence-score filtering using validation-set loss on downstream coding tasks improves Code-LLM performance, with the most beneficial training data varying significantly across different programming tasks.