Search Results for author:
Found 11 papers, 5 papers with code
Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
Large language models (LLM), such as Google's Minerva and OpenAI's GPT families, are becoming increasingly capable of solving mathematical quantitative reasoning problems.
REFACTOR: Learning to Extract Theorems from Proofs
With newly extracted theorems, we show that the existing proofs in the MetaMath database can be refactored.
Zero-shot Object-Level OOD Detection with Context-Aware Inpainting
RONIN conditions the inpainting process with the predicted ID label, drawing the input object closer to the in-distribution domain.
Correction with Backtracking Reduces Hallucination in Summarization
The results show that CoBa is effective and efficient in reducing hallucination, and offers great adaptability and flexibility.
Magnushammer: A Transformer-Based Approach to Premise Selection
By combining \method with a language-model-based automated theorem prover, we further improve the state-of-the-art proof success rate from $57. 0\%$ to $71. 0\%$ on the PISA benchmark using $4$x fewer parameters.
Unsupervised Out-of-Distribution Detection with Diffusion Inpainting
We present a novel approach for this task - Lift, Map, Detect (LMD) - that leverages recent advancement in diffusion models.
Learned Systems Security
We analyze the root causes of potentially-increased attack surface in learned systems and develop a framework for identifying vulnerabilities that stem from the use of ML.
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
In this work, we introduce Draft, Sketch, and Prove (DSP), a method that maps informal proofs to formal proof sketches, and uses the sketches to guide an automated prover by directing its search to easier sub-problems.
Ranked #3 on
Automated Theorem Proving
on miniF2F-valid
(Pass@100 metric)
Does Label Differential Privacy Prevent Label Inference Attacks?
Label differential privacy (label-DP) is a popular framework for training private ML models on datasets with public features and sensitive private labels.
On Attribution of Deepfakes
We discuss the ethical implications of our work, identify where our technique can be used, and highlight that a more meaningful legislative framework is required for a more transparent and ethical use of generative modeling.
Noise Contrastive Estimation for Autoencoding-based One-Class Collaborative Filtering
One-class collaborative filtering (OC-CF) is a common class of recommendation problem where only the positive class is explicitly observed (e. g., purchases, clicks).
