{"total":34,"rows":[{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392,"area":null},{"id":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124,"area":null},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"area":null},{"id":"2311.00059","title":"The Generative AI Paradox: \"What It Can Create, It May Not Understand\"","created":"2023-10-31","cited_by_count":98,"area":null},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56,"area":null},{"id":"2101.11043","title":"Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT","created":"2021-01-26","cited_by_count":41,"area":null},{"id":"2106.01044","title":"Examining the Inductive Bias of Neural Language Models with Artificial Languages","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2304.13060","title":"Injecting structural hints: Using language models to study inductive biases in language learning","created":"2023-04-25","cited_by_count":35,"area":null},{"id":"2203.09397","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","created":"2022-03-17","cited_by_count":28,"area":null},{"id":"2203.10326","title":"Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models","created":"2022-03-19","cited_by_count":28,"area":null},{"id":"2305.19905","title":"How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases","created":"2023-05-31","cited_by_count":23,"area":null},{"id":"2311.09627","title":"Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination","created":"2023-11-16","cited_by_count":23,"area":null},{"id":"2502.12317","title":"Can Language Models Learn Typologically Implausible Languages?","created":"2025-02-17","cited_by_count":23,"area":null},{"id":"2107.05431","title":"CoBERL: Contrastive BERT for Reinforcement Learning","created":"2021-07-12","cited_by_count":21,"area":null},{"id":"2306.03734","title":"A Cross-Linguistic Pressure for Uniform Information Density in Word Order","created":"2023-06-06","cited_by_count":17,"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":"2210.14328","title":"Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models","created":"2022-10-25","cited_by_count":14,"area":null},{"id":"2310.14840","title":"Transparency at the Source: Evaluating and Interpreting Language Models With Access to the True Distribution","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2210.12673","title":"Lexical Generalization Improves with Larger Models and Longer Training","created":"2022-10-23","cited_by_count":9,"area":null},{"id":"2107.06055","title":"On the Difficulty of Translating Free-Order Case-Marking Languages","created":"2021-07-13","cited_by_count":8,"area":null},{"id":"2307.13405","title":"Towards Bridging the Digital Language Divide","created":"2023-07-25","cited_by_count":7,"area":null},{"id":"2106.01207","title":"Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuning","created":"2021-06-02","cited_by_count":5,"area":null},{"id":"2406.02335","title":"Probing the Category of Verbal Aspect in Transformer Language Models","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2606.06479","title":"Pretraining Recurrent Networks without Recurrence","created":"2026-06-04","cited_by_count":5,"area":null},{"id":"2510.12722","title":"Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages","created":"2025-10-14","cited_by_count":4,"area":null},{"id":"2108.03334","title":"Towards Zero-shot Language Modeling","created":"2021-08-06","cited_by_count":3,"area":null},{"id":"2110.05343","title":"Leveraging Transformers for StarCraft Macromanagement Prediction","created":"2021-10-11","cited_by_count":3,"area":null},{"id":"2410.05224","title":"Cookbook: A framework for improving LLM generative abilities via programmatic data generating templates","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2101.12640","title":"Enhancing the Transformer Decoder with Transition-based Syntax","created":"2021-01-29","cited_by_count":1,"area":null},{"id":"2408.05664","title":"Training an NLP Scholar at a Small Liberal Arts College: A Backwards Designed Course Proposal","created":"2024-08-11","cited_by_count":1,"area":null},{"id":"2604.23267","title":"Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2205.06149","title":"Is the Computation of Abstract Sameness Relations Human-Like in Neural Language Models?","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2306.02302","title":"Does Character-level Information Always Improve DRS-based Semantic Parsing?","created":"2023-06-04","cited_by_count":0,"area":null},{"id":"2608.15129","title":"Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models","created":"2026-08-15","cited_by_count":0,"area":null}],"next_cursor":null}