Showing 2025Show all
3 papers · 1 filter
cs.LG2025
Data Reliability Scoring
Yiling Chen, Shi Feng, Paul Kattuman +1
How can we assess the reliability of a dataset without access to ground truth? We introduce the problem of reliability scoring for datasets collected from potentially strategic sou…
cs.AI2025
DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection
Jerry Wang, Fang Yu
Adversarial prompt attacks can significantly alter the reliability of Retrieval-Augmented Generation (RAG) systems by re-ranking them to produce incorrect outputs. In this paper, w…
cs.LG2025
Memorization-Compression Cycles Improve Generalization
Fangyuan Yu
We prove theoretically that generalization improves not only through data scaling but also by compressing internal representations. To operationalize this insight, we introduce the…