{"total":30,"rows":[{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139,"area":null},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108,"area":null},{"id":"2103.13136","title":"Representing Numbers in NLP: a Survey and a Vision","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"area":null},{"id":"2411.03766","title":"Number Cookbook: Number Understanding of Language Models and How to Improve It","created":"2024-11-06","cited_by_count":42,"area":null},{"id":"2106.00969","title":"COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2110.14566","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","created":"2021-10-27","cited_by_count":24,"area":null},{"id":"2403.17169","title":"QuanTemp: A real-world open-domain benchmark for fact-checking numerical claims","created":"2024-03-25","cited_by_count":23,"area":null},{"id":"2404.04963","title":"SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials","created":"2024-04-07","cited_by_count":20,"area":null},{"id":"2305.03598","title":"NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports","created":"2023-05-05","cited_by_count":18,"area":null},{"id":"2109.03137","title":"NumGPT: Improving Numeracy Ability of Generative Pre-trained Models","created":"2021-09-07","cited_by_count":15,"area":null},{"id":"2210.07471","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","created":"2022-10-14","cited_by_count":15,"area":null},{"id":"2211.16482","title":"Chaining Simultaneous Thoughts for Numerical Reasoning","created":"2022-11-29","cited_by_count":14,"area":null},{"id":"2401.14440","title":"Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models","created":"2024-01-25","cited_by_count":14,"area":null},{"id":"2104.07307","title":"NT5?! Training T5 to Perform Numerical Reasoning","created":"2021-04-15","cited_by_count":11,"area":null},{"id":"2109.08207","title":"Numerical reasoning in machine reading comprehension tasks: are we there yet?","created":"2021-09-16","cited_by_count":9,"area":null},{"id":"2205.09898","title":"Let the Model Decide its Curriculum for Multitask Learning","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2305.02993","title":"SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2112.08616","title":"Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2305.06545","title":"GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2111.10756","title":"TraVLR: Now You See It, Now You Don't! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning","created":"2021-11-21","cited_by_count":4,"area":null},{"id":"2211.02098","title":"Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic","created":"2022-11-03","cited_by_count":4,"area":null},{"id":"2309.04635","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2410.13259","title":"From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2211.04417","title":"nBIIG: A Neural BI Insights Generation System for Table Reporting","created":"2022-11-08","cited_by_count":1,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2204.07803","title":"Logical Inference for Counting on Semi-structured Tables","created":"2022-04-16","cited_by_count":0,"area":null},{"id":"2307.05034","title":"Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference","created":"2023-07-11","cited_by_count":0,"area":null},{"id":"2404.14355","title":"Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models","created":"2024-04-22","cited_by_count":0,"area":null},{"id":"2609.33530","title":"E-CONAN (Entailment, CONtradition And Neutral) Diagnostics Dataset Investigating Linguistic Phenomena in Arabic Natural Language Understanding","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}