Workshop
Sat Dec 03 06:55 AM -- 03:00 PM (PST) @ Room 293 - 294 None
MATH-AI: Toward Human-Level Mathematical Reasoning
[ Contact: mathai.neurips2022@gmail.com ]
Mathematical reasoning is a unique aspect of human intelligence and a fundamental building block for scientific and intellectual pursuits. However, learning mathematics is often a challenging human endeavor that relies on expert instructors to create, teach and evaluate mathematical material. From an educational perspective, AI systems that aid in this process offer increased inclusion and accessibility, efficiency, and understanding of mathematics. Moreover, building systems capable of understanding, creating, and using mathematics offers a unique setting for studying reasoning in AI. This workshop will investigate the intersection of mathematics education and AI.
| Introduction and Opening Remarks (Opening Remarks) | |
| Reasoning and Abstraction as Challenges for AI (Invited Talk) | |
| Length Generalization in Quantitative Reasoning (Invited Talk) | |
| Has Progress on Math been Surprising? (Invited Talk) | |
| Poster Session | |
| Lunch Break (Break) | |
| Teaching Algorithmic Reasoning via In-context Learning (Contributed Talk) | |
| Solving Math Word Problems with Process-based and Outcome-based Feedback (Contributed Talk) | |
| ProofNet: A Benchmark for Autoformalizing and Formally Proving Undergraduate-Level Mathematics Problems (Contributed Talk) | |
| Towards Systematic Reasoning with Language Models (Invited Talk) | |
| Coffee Break (Break) | |
| Leveraging Maths to Understand Transformers (Invited Talk) | |
| Learning Mathematical Reasoning for Education (Invited Talk) | |
| MATH-AI: Toward Human-Level Mathematical Reasoning (Discussion Panel) | |
| Closing Remarks | |
| Towards automating formalisation of theorem statements using large language models (Poster) | |
| Improving Compositional Generalization in Math Word Problem Solving (Poster) | |
| Program Synthesis for Integer Sequence Generation (Poster) | |
| Automatic Generation of Socratic Questions for Learning to Solve Math Word Problems (Poster) | |
| Generating Reflexive Polytopes via Sequence Modeling (Poster) | |
| MWP-BERT: A Numeracy-augmented Pre-trained Encoder for Math Word Problems (Poster) | |
| Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems (Poster) | |
| EuclidNet: Deep Visual Reasoning for Constructible Problems in Geometry (Poster) | |
| Teaching Algorithmic Reasoning via In-context Learning (Poster) | |
| A Causal Framework to Quantify Robustness of Mathematical Reasoning with Language Models (Poster) | |
| Learning to Understand Plane Geometry Diagram (Poster) | |
| Estimating Numbers without Regression (Poster) | |
| What is my math transformer doing? Three results on interpretability and generalization (Poster) | |
| Lemma: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions (Poster) | |
| Learn to Select Good Examples with Reinforcement Learning for Semi-structured Mathematical Reasoning (Poster) | |
| Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs (Poster) | |
| Broken Neural Scaling Laws (Poster) | |
| Graph neural networks for Ramsey graphs (Poster) | |
| ProofNet: A Benchmark for Autoformalizing and Formally Proving Undergraduate-Level Mathematics Problems (Poster) | |
| Learning to Reason With Relational Abstractions (Poster) | |
| Out-of-Distribution Generalization in Algorithmic Reasoning Through Curriculum Learning (Poster) | |
| On the Abilities of Mathematical Extrapolation with Implicit Models (Poster) | |
| Solving Math Word Problems with Process-based and Outcome-based Feedback (Poster) | |
| Neural Combinatorial Logic Circuit Synthesis from Input-Output Examples (Poster) | |
| Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic (Poster) | |
| LILA: A Unified Benchmark for Mathematical Reasoning (Poster) | |