Papers by Ismini Lourentzou
MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts? (2025.findings-emnlp)
Copied to clipboard
Muntasir Wahed, Xiaona Zhou, Kiet A. Nguyen, Tianjiao Yu, Nirav Diwan, Gang Wang, Dilek Hakkani-Tür, Ismini Lourentzou
| Challenge: | Recent advances in Large Language Models have significantly enhanced their code generation capabilities, but their robustness against adversarial misuse remains underexplored. |
| Approach: | They introduce a code decomposition attack where a malicious coding task is broken down into subtasks across multiple conversational turns to evade safety filters. |
| Outcome: | The proposed code decomposition attacks exploits multi-turn malicious coding prompts . the proposed model improves rejection rates while preserving coding ability . |
MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multimodal planning use large language models to refine textual steps, but visual object-state alignment and systematic evaluation are underexplored. |
| Approach: | They propose a multimodal multimodal planning framework that uses a 'object-state reasoning chain-of-thought' system to model object-state transitions and generate accurate multimodal plans. |
| Outcome: | The proposed framework improves textual planning by +6.8% and cross-modal alignment by +11.9%. |