conftrace_

data leakage

28 papers

Explore in graph

Co-occurring keywords

large language model (13587) benchmark evaluation (1556) differential privacy (1016) evaluation benchmark (257) benchmark contamination (14) model evaluation (445) pre-training datum (25) fisher information (106) multi-modal learning (1278) privacy preservation (380)

Papers

Retaliatory Attacks Against Federated Unlearning via Data Leakage AAAI 2026
Rethinking Text-based Protein Understanding: Retrieval or LLM? EMNLP 2025
Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation AACL 2025
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges ACL 2025
Investigating How Pre-training Data Leakage Affects Models’ Reproduction and Detection Capabilities EMNLP 2025
The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakage ACL 2025
Do LLMs Behave as Claimed? Investigating How LLMs Follow Their Own Claims using Counterfactual Questions EMNLP 2025
Assessing the Exposure to Public Knowledge in Policy-Protected Description Logic Ontologies IJCAI 2025
Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation EMNLP 2025
Rethinking Cross-Subject Data Splitting for Brain-to-Text Decoding EMNLP 2025
R.R.: Unveiling LLM Training Privacy through Recollection and Ranking ACL 2025
Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference NIPS 2024
EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations NIPS 2024
Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It CVPR 2024
Towards Multiple References Era – Addressing Data Leakage and Limited Reference Diversity in Machine Translation Evaluation ACL 2024
Are We on the Right Way for Evaluating Large Vision-Language Models? NIPS 2024
Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models ACL 2024
Enhancing Data Quality through Simple De-duplication: Navigating Responsible Computational Social Science Research EMNLP 2024
SecureSQL: Evaluating Data Leakage of Large Language Models as Natural Language Interfaces to Databases EMNLP 2024
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients EMNLP 2024
Security Challenges in Natural Language Processing Models EMNLP 2023
Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks EMNLP 2023
A Data-Based Perspective on Transfer Learning CVPR 2023
Measuring Data Leakage in Machine-Learning Models with Fisher Information (Extended Abstract) IJCAI 2022
Memorization vs. Generalization : Quantifying Data Leakage in NLP Performance Evaluation EACL 2021