4 papers
Structural Jailbreaks Generalize but Do Not Compound: A cross-provider and multilingual study of Involuntary In-Context Learning
Tejasvi C. Addagada
Aligned language models fail under two independent pressures: the structural jailbreak class recently formalized as Involuntary In-Context Learning (IICL), which reframes a harmful…
Customer Relationship Intelligence: Integrating CRM and MDM for Enhanced Customer Engagement
Tejasvi c. Addagada
This study examines how Customer Relationship Management (CRM), Master Data Management (MDM), and Customer Knowledge Management (CKM) jointly constitute a Customer Relationship Int…
Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference
Tejasvi C. Addagada
The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests. In multi-tenant deployments t…
Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B
Tejasvi C. Addagada
Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, regulatory compliance, and gener…