Showing 1–20 of 27 results
/ Date/ Name
Feb 26, 2024REFACTOR: Learning to Extract Theorems from ProofsFeb 27, 2025$Q\sharp$: Provably Optimal Distributional RL for LLM Post-TrainingFeb 20, 2023Unsupervised Out-of-Distribution Detection with Diffusion InpaintingAug 3, 2020Noise Contrastive Estimation for Autoencoding-based One-Class Collaborative FilteringJul 4, 2024Orchestrating LLMs with Different PersonalizationsMar 26, 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with AutoformalizationJul 8, 2024On Speeding Up Language Model EvaluationFeb 25, 2022Does Label Differential Privacy Prevent Label Inference Attacks?Oct 24, 2023Correction with Backtracking Reduces Hallucination in SummarizationDec 21, 2024Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning AttacksAug 18, 2025Cognitive Structure Generation: From Educational Priors to Policy OptimizationAug 20, 2020On Attribution of DeepfakesMar 8, 2023Magnushammer: A Transformer-Based Approach to Premise SelectionFeb 16, 2025Graders should cheat: privileged information enables expert-level automated evaluationsFeb 26, 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go BeyondMar 17, 2025INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption ViolationsApr 23, 2025Learning to decode logical circuitsMay 19, 2024Attention to Quantum ComplexityJul 31, 2024Gemma 2: Improving Open Language Models at a Practical SizeMay 21, 2025Pre-training Limited Memory Language Models with Internal and External Knowledge