{"total":19,"rows":[{"id":"2305.16938","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","created":"2023-05-26","cited_by_count":136,"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":"2204.12632","title":"Testing the Ability of Language Models to Interpret Figurative Language","created":"2022-04-26","cited_by_count":67,"area":null},{"id":"2207.14251","title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions","created":"2022-07-28","cited_by_count":57,"area":null},{"id":"2212.01488","title":"Event knowledge in large language models: the gap between the impossible and the unlikely","created":"2022-12-02","cited_by_count":45,"area":null},{"id":"2211.05853","title":"Measuring Reliability of Large Language Models through Semantic Consistency","created":"2022-11-10","cited_by_count":38,"area":null},{"id":"2405.01379","title":"Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving","created":"2024-05-02","cited_by_count":35,"area":null},{"id":"2201.02387","title":"The Defeat of the Winograd Schema Challenge","created":"2022-01-07","cited_by_count":25,"area":null},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19,"area":null},{"id":"2409.05653","title":"WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Case","created":"2024-09-09","cited_by_count":9,"area":null},{"id":"2204.04813","title":"Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2206.14729","title":"longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks","created":"2022-06-29","cited_by_count":8,"area":null},{"id":"2312.01276","title":"Toward best research practices in AI Psychology","created":"2023-12-03","cited_by_count":8,"area":null},{"id":"2306.03882","title":"Causal interventions expose implicit situation models for commonsense language understanding","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2401.06640","title":"Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2405.16277","title":"Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2402.13372","title":"EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2210.16989","title":"Validity Assessment of Legal Will Statements as Natural Language Inference","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2308.15235","title":"PronounFlow: A Hybrid Approach for Calibrating Pronouns in Sentences","created":"2023-08-29","cited_by_count":0,"area":null}],"next_cursor":null}