Analysing Mathematical Reasoning Abilities of Neural Models
Mathematical reasoning---a core ability within human intelligence---presents some unique challenges as a domain: we do not come to understand and solve mathematical problems primarily on the back of experience and evidence, but on the basis of inferring, learning, and exploiting laws, axioms, and symbol manipulation rules. In this paper, we present a new challenge for the evaluation (and eventually the design) of neural architectures and similar system, developing a task suite of mathematics problems involving sequential questions and answers in a free-form textual input/output format. The structured nature of the mathematics domain, covering arithmetic, algebra, probability and calculus, enables the construction of training and test splits designed to clearly illuminate the capabilities and failure-modes of different architectures, as well as evaluate their ability to compose and relate knowledge and learned processes. Having described the data generation process and its potential future expansions, we conduct a comprehensive analysis of models from two broad classes of the most powerful sequence-to-sequence architectures and find notable differences in their ability to resolve mathematical problems and generalize their knowledge.
Code (7)
Tasks
Mathematical Question AnsweringMathematical ReasoningMath Word Problem SolvingQuestion AnsweringSimilar Papers 제목 키워드 기반
A Scalable Approach for Analysing Multi-Agent Systems with Heterogeneous Stochastic Packet Loss
An important aspect in jointly analysing networked control systems and their communication is to model the networking in a sufficiently rich but at the same time mathematically tractable way. As such, this paper improves…
MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs
Recent large language models (LLMs) have demonstrated versatile capabilities in long-context scenarios. Although some recent benchmarks have been developed to evaluate the long-context capabilities of LLMs, there is a la…
Information RetrievalMathematical ReasoningLexPam: Legal Procedure Awareness-Guided Mathematical Reasoning
The legal mathematical reasoning ability of LLMs is crucial when applying them to real-world scenarios, as it directly affects the credibility of the LLM. While existing legal LLMs can perform general judicial question a…
Mathematical ReasoningQuestion AnsweringAtomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities
Large Language Models (LLMs) have demonstrated outstanding performance in mathematical reasoning capabilities. However, we argue that current large-scale reasoning models primarily rely on scaling up training datasets wi…
Mathematical ReasoningIs Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist
Exceptional mathematical reasoning ability is one of the key features that demonstrate the power of large language models (LLMs). How to comprehensively define and evaluate the mathematical abilities of LLMs, and even re…
GSM8KMathMathematical Reasoning