mlsanityData to 14 Oct 2026

ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler

arXiv 2210.10105 ↗First posted 18 Oct 2022cs.AI cs.CLcited by 14

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

Numerical reasoning over text is a challenging task of Artificial Intelligence (AI), requiring reading comprehension and numerical reasoning abilities. Previous approaches use numerical reasoning programs to represent the reasoning process. However, most works do not separate the generation of operators and operands, which are key components of a numerical reasoning program, thus limiting their ability to generate such programs for complicated tasks. In this paper, we introduce the numEricaL reASoning with adapTive symbolIc Compiler (ELASTIC) model, which is constituted of the RoBERTa as the Encoder and a Compiler with four modules: Reasoning Manager, Operator Generator, Operands Generator, and Memory Register. ELASTIC is robust when conducting complicated reasoning. Also, it is domain agnostic by supporting the expansion of diverse operators without caring about the number of operands it contains. Experiments show that ELASTIC achieves 68.96 and 65.21 of execution accuracy and program accuracy on the FinQA dataset and 83.00 program accuracy on the MathQA dataset, outperforming previous state-of-the-art models significantly.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 22 of its 45 references that are in the map. First posted on arXiv 18 Oct 2022.

Builds on

22 of 45 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  7. 2017Inductive Representation Learning on Large Graphscited by 6,320
  8. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  9. 2021Program Synthesis with Large Language Modelscited by 3,637
  10. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  11. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  12. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
10 more
  1. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  2. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 662
  3. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  4. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 318
  5. 2020Injecting Numerical Reasoning Skills into Language Modelscited by 133
  6. 2019NumNet: Machine Reading Comprehension with Numerical Reasoningcited by 59
  7. 2018Translating a Math Word Problem to an Expression Treecited by 57
  8. 2018Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problemscited by 49
  9. 2020Semantically-Aligned Universal Tree-Structured Solver for Math Word Problemscited by 35
  10. 2020Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problemcited by 31

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 5; 2024: 6; 2025: 0; 2026: 1.

14 papers.

Sort:

By area:

  1. 2023A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagramcited by 56
  2. 2024Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectivescited by 30
  3. 2024QuanTemp: A real-world open-domain benchmark for fact-checking numerical claimscited by 23
  4. 2024TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Datacited by 19
  5. 2024Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Modelscited by 14
  6. 2023SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQAcited by 9
  7. 2022APOLLO: An Optimized Training Approach for Long-form Numerical Reasoningcited by 8
  8. 2022A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directionscited by 7
  9. 2023An Expression Tree Decoding Strategy for Mathematical Equation Generationcited by 4
  10. 2023Retrieval-Augmented Chain-of-Thought in Semi-structured Domainscited by 4
  11. 2024Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trendscited by 3
  12. 2024GAPS: Geometry-Aware Problem Solvercited by 1
2 more
  1. 2023Comprehensive Solution Program Centric Pretraining for Table-and-Text Hybrid Numerical Reasoningcited by 0
  2. 2026Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Scalable Chain of Thoughts via Elastic Reasoning
  2. 2023Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models
  3. 2022Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems
  4. 2023Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning
  5. 2024HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoning
  6. 2025Primender Sequence: A Novel Mathematical Construct for Testing Symbolic Inference and AI Reasoning
  7. 2026Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery
  8. 2023Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems