{"total":34,"rows":[{"id":"2212.06801","title":"A fine-grained comparison of pragmatic language understanding in humans and language models","created":"2022-12-13","cited_by_count":70,"area":null},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68,"area":null},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2106.02902","title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT","created":"2021-06-05","cited_by_count":40,"area":null},{"id":"2106.01195","title":"Figurative Language in Recognizing Textual Entailment","created":"2021-06-02","cited_by_count":26,"area":null},{"id":"2406.05183","title":"The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More","created":"2024-06-07","cited_by_count":25,"area":null},{"id":"2109.02071","title":"End-to-End Self-Debiasing Framework for Robust NLU Training","created":"2021-09-05","cited_by_count":24,"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":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19,"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":"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":"2211.11187","title":"L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi","created":"2022-11-21","cited_by_count":10,"area":null},{"id":"2212.05421","title":"Feature-Level Debiased Natural Language Understanding","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2207.06897","title":"Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language","created":"2022-07-14","cited_by_count":9,"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":"2204.01437","title":"Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning","created":"2022-04-04","cited_by_count":6,"area":null},{"id":"2502.09690","title":"Trust at Your Own Peril: A Mixed Methods Exploration of the Ability of Large Language Models to Generate Expert-Like Systems Engineering Artifacts and a Characterization of Failure Modes","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2306.01907","title":"A Simple yet Effective Self-Debiasing Framework for Transformer Models","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2310.14418","title":"REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2508.17953","title":"Understanding Subword Compositionality of Large Language Models","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2111.06644","title":"Variation and generality in encoding of syntactic anomaly information in sentence embeddings","created":"2021-11-12","cited_by_count":2,"area":null},{"id":"2203.16682","title":"To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo","created":"2022-03-30","cited_by_count":2,"area":null},{"id":"2311.00292","title":"IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2110.11899","title":"Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmark","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2110.14764","title":"Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2210.07566","title":"A Survey of Parameters Associated with the Quality of Benchmarks in NLP","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2404.12013","title":"Sequential Compositional Generalization in Multimodal Models","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2508.21569","title":"L3Cube-MahaSTS: A Marathi Sentence Similarity Dataset and Models","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2103.06198","title":"Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling","created":"2021-03-10","cited_by_count":0,"area":null},{"id":"2201.03521","title":"Polish Natural Language Inference and Factivity -- an Expert-based Dataset and Benchmarks","created":"2022-01-10","cited_by_count":0,"area":null},{"id":"2306.04523","title":"Can current NLI systems handle German word order? Investigating language model performance on a new German challenge set of minimal pairs","created":"2023-06-07","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":"2311.11085","title":"Compositional Fusion of Signals in Data Embedding","created":"2023-11-18","cited_by_count":0,"area":null},{"id":"2505.16522","title":"Large Language Models Are Still Misled by Simple Bias Ensembles","created":"2025-05-22","cited_by_count":0,"area":null}],"next_cursor":null}