Khyathi Chandu

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness

The Generative AI Paradox: “What It Can Create, It May Not Understand”

LUMOS: Towards Language Agents that are Unified, Modular, and Open Source

The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning