Search Results for author: Xujie Si

Found 20 papers, 9 papers with code

Library Learning Doesn't: The Curious Case of the Single-Use "Library"

1 code implementation26 Oct 2024 Ian Berlot-Attwell, Frank Rudzicz, Xujie Si

Advances in Large Language Models (LLMs) have spurred a wave of LLM library learning systems for mathematical reasoning.

Math Mathematical Reasoning

APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts

1 code implementation19 Jun 2024 Honghua Dong, Qidong Su, Yubo Gao, Zhaoyu Li, Yangjun Ruan, Gennady Pekhimenko, Chris J. Maddison, Xujie Si

Large Language Models (LLMs) have become increasingly capable of handling diverse tasks with the aid of well-crafted prompts and integration of external tools, but as task complexity rises, the workflow involving LLMs can be complicated and thus challenging to implement and maintain.

Language Modelling Large Language Model

Autoformalizing Euclidean Geometry

1 code implementation27 May 2024 Logan Murphy, Kaiyu Yang, Jialiang Sun, Zhaoyu Li, Anima Anandkumar, Xujie Si

One challenge in Euclidean geometry is that informal proofs rely on diagrams, leaving gaps in texts that are hard to formalize.

Math

Code Repair with LLMs gives an Exploration-Exploitation Tradeoff

no code implementations26 May 2024 Hao Tang, Keya Hu, Jin Peng Zhou, Sicheng Zhong, Wei-Long Zheng, Xujie Si, Kevin Ellis

Iteratively improving and repairing source code with large language models (LLMs), known as refinement, has emerged as a popular way of generating programs that would be too complex to construct in one shot.

Code Repair Language Modelling +3

A Survey on Deep Learning for Theorem Proving

1 code implementation15 Apr 2024 Zhaoyu Li, Jialiang Sun, Logan Murphy, Qidong Su, Zenan Li, Xian Zhang, Kaiyu Yang, Xujie Si

Theorem proving is a fundamental aspect of mathematics, spanning from informal reasoning in natural language to rigorous derivations in formal systems.

Automated Theorem Proving Deep Learning +2

Learning Minimal Neural Specifications

no code implementations6 Apr 2024 Chuqin Geng, Zhaoyue Wang, Haolin Ye, Saifei Liao, Xujie Si

Formal verification is only as good as the specification of a system, which is also true for neural network verification.

G4SATBench: Benchmarking and Advancing SAT Solving with Graph Neural Networks

1 code implementation29 Sep 2023 Zhaoyu Li, Jinpei Guo, Xujie Si

Graph neural networks (GNNs) have recently emerged as a promising approach for solving the Boolean Satisfiability Problem (SAT), offering potential alternatives to traditional backtracking or local search SAT solvers.

Benchmarking

Chronosymbolic Learning: Efficient CHC Solving with Symbolic Reasoning and Inductive Learning

2 code implementations2 May 2023 Ziyan Luo, Xujie Si

Solving Constrained Horn Clauses (CHCs) is a fundamental challenge behind a wide range of verification and analysis tasks.

Can ChatGPT Pass An Introductory Level Functional Language Programming Course?

no code implementations29 Apr 2023 Chuqin Geng, Yihan Zhang, Brigitte Pientka, Xujie Si

The recent introduction of ChatGPT has drawn significant attention from both industry and academia due to its impressive capabilities in solving a diverse range of tasks, including language translation, text summarization, and computer programming.

Text Summarization

Scalar Invariant Networks with Zero Bias

no code implementations15 Nov 2022 Chuqin Geng, Xiaojie Xu, Haolin Ye, Xujie Si

However, we argue that biases can be disregarded for some image-related tasks such as image classification, by considering the intrinsic distribution of images in the input space and desired model properties from first principles.

Fairness Image Classification

NSNet: A General Neural Probabilistic Framework for Satisfiability Problems

1 code implementation7 Nov 2022 Zhaoyu Li, Xujie Si

We present the Neural Satisfiability Network (NSNet), a general neural framework that models satisfiability problems as probabilistic inference and meanwhile exhibits proper explainability.

Graph Neural Network

Towards Reliable Neural Specifications

no code implementations28 Oct 2022 Chuqin Geng, Nham Le, Xiaojie Xu, Zhaoyue Wang, Arie Gurfinkel, Xujie Si

We show that by using NAP, we can verify a significant region of the input space, while still recalling 84% of the data on MNIST.

Adversarial Robustness

Novice Type Error Diagnosis with Natural Language Models

no code implementations7 Oct 2022 Chuqin Geng, Haolin Ye, Yixuan Li, Tianyu Han, Brigitte Pientka, Xujie Si

Strong static type systems help programmers eliminate many errors without much burden of supplying type annotations.

Language Modelling Vocal Bursts Type Prediction

Graph Contrastive Pre-training for Effective Theorem Reasoning

no code implementations24 Aug 2021 Zhaoyu Li, Binghong Chen, Xujie Si

Interactive theorem proving is a challenging and tedious process, which requires non-trivial expertise and detailed low-level instructions (or tactics) from human experts.

Automated Theorem Proving Contrastive Learning +1

Techniques for Symbol Grounding with SATNet

1 code implementation NeurIPS 2021 Sever Topan, David Rolnick, Xujie Si

Many experts argue that the future of artificial intelligence is limited by the field's ability to integrate symbolic logical reasoning into deep learning architectures.

Logical Reasoning Visual Reasoning

Prioritized Unit Propagation with Periodic Resetting is (Almost) All You Need for Random SAT Solving

no code implementations4 Dec 2019 Xujie Si, Yujia Li, Vinod Nair, Felix Gimeno

We share this observation in the hope that it helps the SAT community better understand the hardness of random instances used in competitions and inspire other interesting ideas on SAT solving.

Synthesizing Datalog Programs Using Numerical Relaxation

no code implementations1 Jun 2019 Xujie Si, Mukund Raghothaman, Kihong Heo, Mayur Naik

The problem of learning logical rules from examples arises in diverse fields, including program synthesis, logic programming, and machine learning.

Program Synthesis

Learning a Meta-Solver for Syntax-Guided Program Synthesis

no code implementations ICLR 2019 Xujie Si, Yuan Yang, Hanjun Dai, Mayur Naik, Le Song

Our framework consists of three components: 1) an encoder, which embeds both the logical specification and grammar at the same time using a graph neural network; 2) a grammar adaptive policy network which enables learning a transferable policy; and 3) a reinforcement learning algorithm that jointly trains the specification and grammar embedding and adaptive policy.

Graph Neural Network Meta-Learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.