{"total":20,"rows":[{"id":"2407.14985","title":"Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data","created":"2024-07-20","cited_by_count":85,"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":"2101.00376","title":"RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge","created":"2021-01-02","cited_by_count":61,"area":null},{"id":"2106.03634","title":"PROST: Physical Reasoning of Objects through Space and Time","created":"2021-06-07","cited_by_count":48,"area":null},{"id":"2203.08075","title":"Things not Written in Text: Exploring Spatial Commonsense from Visual Signals","created":"2022-03-15","cited_by_count":41,"area":null},{"id":"2104.08161","title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2305.14824","title":"Mitigating Temporal Misalignment by Discarding Outdated Facts","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2112.04596","title":"Refined Commonsense Knowledge from Large-Scale Web Contents","created":"2021-11-30","cited_by_count":19,"area":null},{"id":"2406.14394","title":"SEC-QA: A Systematic Evaluation Corpus for Financial QA","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2104.12922","title":"One Billion Audio Sounds from GPU-enabled Modular Synthesis","created":"2021-04-27","cited_by_count":11,"area":null},{"id":"2307.05454","title":"Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2311.01866","title":"Towards Concept-Aware Large Language Models","created":"2023-11-03","cited_by_count":6,"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":"2210.12694","title":"Do Language Models Understand Measurements?","created":"2022-10-23","cited_by_count":2,"area":null},{"id":"2304.10739","title":"KitchenScale: Learning to predict ingredient quantities from recipe contexts","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2102.00997","title":"Inferring spatial relations from textual descriptions of images","created":"2021-02-01","cited_by_count":1,"area":null},{"id":"2303.04532","title":"Class Cardinality Comparison as a Fermi Problem","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2403.13666","title":"Grounding Spatial Relations in Text-Only Language Models","created":"2024-03-20","cited_by_count":1,"area":null},{"id":"2508.15274","title":"TComQA: Extracting Temporal Commonsense from Text","created":"2025-08-21","cited_by_count":0,"area":null}],"next_cursor":null}