Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Steering by Influence: Curvature Aware Data Weighting for Activation Steering
James A. E. Dixon, Stephen J. Roberts, Francesco Quinzan
Inference-time steering offers cheap, fine-grained control over a language model's outputs by estimating a concept's representation in activation space and shifting activations tow…
cs.LG2026
Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs
Noor Munir, Francesco Quinzan, Stephen Roberts
Code large language model (Code LLM) assistants generate code from heterogeneous development contexts, including open files, imported modules, pasted snippets, and comments, much o…
cs.LG2026
Detecting Contaminated Code-Generation Prompt Batches via Influence Functions
Francesco Quinzan, Noor Munir, Yishun Lu +1
Large language models (LLMs) are increasingly used for code generation, yet they remain vulnerable to prompts that elicit insecure implementations. Existing defenses typically rely…