Wenda Li

Neural Theorem Proving for Verification Conditions: A Real-World Benchmark

F1-Reasoner: Synthesizing Verifiable Reasoning Data From Formal Math Statements

PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains

Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving

Multi-language Diversity Benefits Autoformalization

Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization

Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe

Proving Theorems Recursively

Multilingual Mathematical Autoformalization

End-to-End Ontology Learning with Large Language Models