8 papers
Multi-Objective Bayesian Optimization for Model Merging
Utkarsh Agarwal, Vamshi Bonagiri, Raul Astudillo +1
Model merging combines trained models directly in weight space, offering a compute-efficient alternative to additional fine-tuning. Selecting merge parameters is nevertheless diffi…
Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
Vamshi Krishna Bonagiri, Ponnurangam Kumaragurum, Khanh Nguyen +1
As Large Language Model (LLM) agents increasingly operate in complex environments with real-world consequences, their safety becomes critical. While uncertainty quantification is w…
Cognitive Digital Twins: Ethical Risks and Governance for AI Systems That Model the Mind
Vamshi Krishna Bonagiri, Juan Nicolas Sepulveda-Arias, Abdoul Jalil Djiberou Mahamadou +1
As AI systems become increasingly persistent and personalized, they make possible a class of technologies that we call cognitive digital twins (CDTs): dynamic computational represe…
Efficient Safety Benchmarking via Item Response Theory
Fabio Spagliardi, MÃrian Silva, Ayan Datta +3
Safety benchmarks for language models are typically evaluated using static paradigms that treat all items as equally informative for all models, an assumption that is particularly…
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
Krishak Aneja, Manas Mittal, Anmol Goel +2
Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work lin…
Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds
Anish R Joishy, Ishwar B Balappanawar, Vamshi Krishna Bonagiri +3
A fundamental challenge in reasoning is navigating hypothetical, counterfactual worlds where logic may conflict with ingrained knowledge. We investigate this frontier for Large Lan…