Solving Quantitative Reasoning Problems with Language Models
Explore this paper's citation graph
- Type
- preprint
- Published
- 2022-06-29
- Cited by
- 1,932
- References
- 71
- Access
- Open access
- OpenAlex
- https://openalex.org/W4283768109
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:250144408
Keywords
Computer science, Range (aeronautics), Language model, Qualitative reasoning, State (computer science)
References
- Mizar in a Nutshell
- Learning to Solve Arithmetic Word Problems with Verb Categorization
- Parsing Algebraic Word Problems into Equations
- SymPy: Symbolic computing in Python
- Reinforcement Learning of Theorem Proving
- A Simple Method for Commonsense Reasoning
- EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- The Curious Case of Neural Text Degeneration
- Semantic Search in Millions of Equations
- Measuring Massive Multitask Language Understanding
- Generative Language Modeling for Automated Theorem Proving
- IsarStep: a Benchmark for High-level Mathematical Reasoning
- Fast and Slow Enigmas and Parental Guidance
- NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks
- Scaling Up Models and Data with t5x and seqio
- Competition-level code generation with AlphaCode
- Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
- Autoformalization with Large Language Models
- A neural network solves, explains, and generates university math problems by program synthesis and few-shot learning at human level
Cited by
- Neural Status Registers
- STaR: Bootstrapping Reasoning With Reasoning
- Formal Specifications from Natural Language
- A Survey in Mathematical Language Processing
- Formal Algorithms for Transformers
- Few-shot Adaptation Works with UnpredicTable Data
- Meaning without reference in large language models
- Higher Cognition: A Mechanical Perspective
- Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment
- Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans
- Improving alignment of dialogue agents via targeted human judgements
- Learning by Distilling Context
- Complexity-Based Prompting for Multi-Step Reasoning
- Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought
- Explaining Patterns in Data with Language Models via Interpretable Autoprompting
- Learning to Reason With Relational Abstractions
- Out-of-Distribution Generalization in Algorithmic Reasoning Through Curriculum Learning
- Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems
- Mind's Eye: Grounded Language Model Reasoning through Simulation
- Transcending Scaling Laws with 0.1% Extra Compute
Related papers
- Combined Reasoning of Qualitative and Quantitative of Relations between Time Intervals
- QUALITATIVE REASONING FOR DYNAMIC SYSTEM :MODELING AND SIMULATION
- A developmental study on the proportiona reasoning in school age children (II): -Qualitative reasoning and quantitative reasoning-
- Effects of Promoting Argumentation on Students' Reasoning in Physics.
- Methods of Reasoning in Scientific Discovery
- Identify Student’s Scientific Reasoning Skill in Straight Motion Material
- Deviation and Difficulty in Different Types of Reasoning