Pacchiardi, Lorenzo
- How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
2023/09/26 by Lorenzo Pacchiardi, Pacchiardi, Lorenzo, Alex Chan +13 · 13 citations
Computer Science · Psychology · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Deception detection and forensic psychology #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling
- General Scales Unlock AI Evaluation with Explanatory and Predictive Power
2025/03/09 by Zhou, Lexin, Pacchiardi, Lorenzo, Martínez-Plumed, Fernando +23 · 7 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences
- 100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances
2024/09/05 by Lorenzo Pacchiardi, Pacchiardi, Lorenzo, Lucy G. Cheke +3 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Machine Learning and Data Classification #Natural Language Processing Techniques
- Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture
2025/02/21 by Burden, John, Tešić, Marko, Pacchiardi, Lorenzo +1 · 4 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
2025/09/12 by Cencerrado, Iván Vicente Moreno, Masdemont, Arnau Padrés, Hawthorne, Anton Gonzalvez +2 · 3 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- PredictaBoard: Benchmarking LLM Score Predictability
2025/02/20 by Pacchiardi, Lorenzo, Voudouris, Konstantinos, Slater, Ben +4 · 2 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (stat.ML)