{"total":20,"rows":[{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2101.10713","title":"Exploring Transitivity in Neural NLI Models through Veridicality","created":"2021-01-26","cited_by_count":15,"area":null},{"id":"2109.02102","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2208.04826","title":"Compositional Evaluation on Japanese Textual Entailment and Similarity","created":"2022-08-09","cited_by_count":14,"area":null},{"id":"2309.11975","title":"Inferring Capabilities from Task Performance with Bayesian Triangulation","created":"2023-09-21","cited_by_count":13,"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":"2305.06408","title":"Accelerating Batch Active Learning Using Continual Learning Techniques","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2106.01077","title":"SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2110.01509","title":"DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models","created":"2021-10-04","cited_by_count":7,"area":null},{"id":"2210.12795","title":"Realistic Data Augmentation Framework for Enhancing Tabular Reasoning","created":"2022-10-23","cited_by_count":4,"area":null},{"id":"2204.06283","title":"Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding","created":"2022-04-13","cited_by_count":3,"area":null},{"id":"2307.03313","title":"InfoSync: Information Synchronization across Multilingual Semi-structured Tables","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2305.12951","title":"Cross-functional Analysis of Generalisation in Behavioural Learning","created":"2023-05-22","cited_by_count":2,"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":"2311.08481","title":"Functionality learning through specification instructions","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2408.05023","title":"Investigating a Benchmark for Training-set free Evaluation of Linguistic Capabilities in Machine Reading Comprehension","created":"2024-08-09","cited_by_count":0,"area":null},{"id":"2508.19402","title":"One Joke to Rule them All? On the (Im)possibility of Generalizing Humor","created":"2025-08-26","cited_by_count":0,"area":null}],"next_cursor":null}