2 papers
cs.CR2026
The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning
Manit Baser, Aditya Nawal, Dinil Mon Divakaran +1
Open-weight LLMs give downstream users control over the inference stack, but this flexibility can undermine post-release guarantees that sensitive knowledge has been modified or re…
cs.CL2026
Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
Aditya Nawal, Manit Baser, Mohan Gurusamy
AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the gene…