会员服务
Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
Arxiv
0+阅读 · 3月18日
Understanding and Mitigating Dataset Corruption in LLM Steering
Arxiv
0+阅读 · 3月3日
The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal Techniques
Arxiv
0+阅读 · 3月9日
Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
Arxiv
0+阅读 · 2月17日
Provably robust learning of regression neural networks using $β$-divergences
Arxiv
0+阅读 · 2月9日
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models
Arxiv
0+阅读 · 2月12日
LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces
Arxiv
0+阅读 · 2月15日
UniCode: Augmenting Evaluation for Code Reasoning
Arxiv
0+阅读 · 2月14日
Rethinking the effects of data contamination in Code Intelligence
Arxiv
0+阅读 · 2月6日
Multi-Cue Anomaly Detection and Localization under Data Contamination
Arxiv
0+阅读 · 2月4日
Quantifying Data Contamination in Psychometric Evaluations of LLMs
Arxiv
0+阅读 · 1月30日
Multi-Cue Anomaly Detection and Localization under Data Contamination
Arxiv
0+阅读 · 1月30日
QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption
Arxiv
0+阅读 · 2月3日
AI-generated data contamination erodes pathological variability and diagnostic reliability
Arxiv
0+阅读 · 2月2日
Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
Arxiv
0+阅读 · 1月16日
参考链接
微信扫码咨询专知VIP会员
Top