Cancedda, Nicola

Toolformer: Language Models Can Teach Themselves to Use Tools

Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · arXiv

Robot Manipulation and LearningAI-based Problem Solving and Planning

Cited by 1,150

HalluLens: LLM Hallucination Benchmark

Bang, Y., Ji, Z., Schelten, A., Hartshorn, A., Fowler, T., Zhang, C., Cancedda, N., & Fung, P. (2025) · Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Topic ModelingNatural Language Processing Techniques

Cited by 41

Robust LLM safeguarding via refusal feature adversarial training

Yu, L., Do, V., Hambardzumyan, K., & Cancedda, N. (2024) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 3

AIRA_2: Overcoming Bottlenecks in AI Research Agents

Hambardzumyan, K., Baldwin, N., Toledo, E., Hazra, R., Kuchnik, M., Omari, B. A., Foster, T. S., Protopopov, A., Gagnon-Audet, J.-C., Mediratta, I., et al. (2026) · arXiv

Artificial Intelligence ApplicationsScientific Computing and Data Management

Cited by 1

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

Toledo, E., Hambardzumyan, K., Josifoski, M., Hazra, R., Baldwin, N., Audran-Reiss, A., Kuchnik, M., Magka, D., Jiang, M., Lupidi, A. M., et al. (2025) · arXiv

Machine Learning and Data ClassificationEvolutionary Algorithms and Applications

Cited by 0