Lisa Alazraki

large language model (4) mathematical reasoning (3) synthetic data generation (1) data selection (1) tool use (1) tool selection (1) chain-of-thought prompting (1) compositional reasoning (1) commonsense reasoning (1) error correction (1) implicit learning (1) out-of-distribution performance (1) model brittleness (1) llm reasoning (1) error learning (1) corrective rationale (1) test-time reasoning (1) mistake learning (1) in-context learning (1)