No article text was recorded for this version.
numerical extrapolation gap
Version 2 of 290 papers120 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model
- Blog: Neural Status Registers
- Blog: Diversify Your Datasets: Analyzing Generalization via Controlled Variance in Adversarial Datasets
- Blog: TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models
- Blog: Have You Seen That Number? Investigating Extrapolation in Question Answering Models
- Blog: Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning
- Blog: Measuring abstract reasoning in neural networks
- Blog: Do NLP Models Know Numbers? Probing Numeracy in Embeddings
- Blog: Unravelling the Logic: Investigating the Generalisation of Transformers in Numerical Satisfiability Problems
- Blog: Slot Abstractors: Toward Scalable Abstract Visual Reasoning
- Blog: TraVLR: Now You See It, Now You Don’t! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning
- Blog: Neural Arithmetic Units
- Blog: Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks
- Blog: Do Language Models Understand Measurements?
- Blog: TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models
- Blog: Joint translation and unit conversion for end-to-end localization
- Blog: Machine learning detects terminal singularities
- Blog: oLMpics - On what Language Model Pre-training Captures
- Blog: A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics
- Blog: Neural Power Units
- Blog: MarkQA: A large scale KBQA dataset with numerical reasoning
- Blog: Symbolic Brittleness in Sequence Models: On Systematic Generalization in Symbolic Mathematics
- Blog: Can a Large Language Model Learn Matrix Functions In Context?
- Blog: Knowledge Graph Reasoning over Entities and Numerical Values
- Blog: Generalizable Reasoning through Compositional Energy Minimization
- Blog: Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning
- Blog: What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment
- Blog: Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics
- Blog: Large Language Models' Understanding of Math: Source Criticism and Extrapolation
- Blog: How Neural Nets Work
- Blog: Laying Anchors: Semantically Priming Numerals in Language Modeling
- Blog: Unveiling the Visual Counting Bottleneck in Vision-Language Models
- Blog: Learning to solve arithmetic problems with a virtual abacus
- Blog: A Primer for Neural Arithmetic Logic Modules
- Blog: Intégration du raisonnement numérique dans les modèles de langue : État de l'art et direction de recherche
- Blog: Exploring Mathematical Extrapolation of Large Language Models with Synthetic Data
- Blog: Methods for Numeracy-Preserving Word Embeddings
- Blog: Towards Large Language Models as Copilots for Theorem Proving in Lean
- Blog: Neural Power Units
- Blog: Learning Representations that Support Extrapolation
- Blog: Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data
- Blog: Beyond Transformers for Function Learning
- Blog: NUMCoT: Numerals and Units of Measurement in Chain-of-Thought Reasoning using Large Language Models
- Blog: Regress, Don't Guess - A Regression-like Loss on Number Tokens for Language Models
- Blog: CYUT at SemEval-2024 Task 7: A Numerals Augmentation and Feature Enhancement Approach to Numeral Reading Comprehension
- Blog: A Number Sense as an Emergent Property of the Manipulating Brain
- Blog: Investigating Symbolic Capabilities of Large Language Models
- Blog: Neural Arithmetic Logic Units
- Blog: Neural Status Registers
- Blog: ControlMath: Controllable Data Generation Promotes Math Generalist Models
- Blog: Machine learning detects terminal singularities
- Blog: How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
- Blog: Reasoning with Language Model Prompting: A Survey
- Blog: Improving the Robustness of Neural Multiplication Units with Reversible Stochasticity
- Blog: UTMath: A Benchmark for Math Evaluation with Unit Test
- Blog: Can neural networks extrapolate? Discussion of a theorem by Pedro Domingos
- Blog: Learning Multi-Step Reasoning by Solving Arithmetic Tasks
- Blog: Language Models Need Inductive Biases to Count Inductively
- Blog: A Closer Look at In-Context Learning under Distribution Shifts
- Blog: ChemAlgebra: Algebraic Reasoning on Chemical Reactions
Showing 60 of 90 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_numerical_extrapolation_gap_e2e74af9,
title = {numerical extrapolation gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/numerical-extrapolation-gap/rdr_e2e74af92467466282b2bc8a6dd4b0e9},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_numerical_extrapolation_gap_e2e74af9_v2,
title = {numerical extrapolation gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/numerical-extrapolation-gap/rdr_e2e74af92467466282b2bc8a6dd4b0e9/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}