Tianle Li

Search Arena: Analyzing Search-Augmented LLMs

How to Evaluate Reward Models for RLHF

From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline

Bench-O-Matic: Automating Benchmark Curation from Crowdsourced Data

Prompt-to-Leaderboard: Prompt-Adaptive LLM Evaluations

AutoEval Done Right: Using Synthetic Data for Model Evaluation

Project MPG: towards a generalized performance quotient for LLM intelligence