{"total":110,"rows":[{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341,"area":null},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334,"area":"lr"},{"id":"2110.08387","title":"Generated Knowledge Prompting for Commonsense Reasoning","created":"2021-10-15","cited_by_count":214,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139,"area":null},{"id":"2205.09328","title":"TransTab: Learning Transferable Tabular Transformers Across Tables","created":"2022-05-19","cited_by_count":132,"area":null},{"id":"2212.10535","title":"A Survey of Deep Learning for Mathematical Reasoning","created":"2022-12-20","cited_by_count":124,"area":"lr"},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121,"area":null},{"id":"2106.09231","title":"Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases","created":"2021-06-17","cited_by_count":107,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88,"area":null},{"id":"2110.05006","title":"Pre-trained Language Models in Biomedical Domain: A Systematic Survey","created":"2021-10-11","cited_by_count":87,"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":"2401.11624","title":"In-context Learning with Retrieved Demonstrations for Language Models: A Survey","created":"2024-01-21","cited_by_count":70,"area":null},{"id":"2106.06937","title":"Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning","created":"2021-06-13","cited_by_count":65,"area":null},{"id":"2310.06213","title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","created":"2023-10-10","cited_by_count":64,"area":null},{"id":"2303.16421","title":"ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models","created":"2023-03-29","cited_by_count":63,"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":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60,"area":null},{"id":"2106.04571","title":"TIMEDIAL: Temporal Commonsense Reasoning in Dialog","created":"2021-06-08","cited_by_count":55,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"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":"2105.12544","title":"Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization","created":"2021-05-26","cited_by_count":46,"area":null},{"id":"2305.03695","title":"Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements","created":"2023-05-05","cited_by_count":44,"area":null},{"id":"2210.03078","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","created":"2022-10-06","cited_by_count":43,"area":null},{"id":"2411.03766","title":"Number Cookbook: Number Understanding of Language Models and How to Improve It","created":"2024-11-06","cited_by_count":42,"area":null},{"id":"2202.05148","title":"Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET","created":"2022-02-10","cited_by_count":41,"area":null},{"id":"2106.00969","title":"COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2404.01854","title":"IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces","created":"2024-04-02","cited_by_count":39,"area":"lr"},{"id":"2201.12438","title":"Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey","created":"2022-01-28","cited_by_count":38,"area":null},{"id":"2110.08182","title":"The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color","created":"2021-10-15","cited_by_count":32,"area":null},{"id":"2104.05837","title":"Relational World Knowledge Representation in Contextual Language Models: A Review","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2205.12247","title":"GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models","created":"2022-05-24","cited_by_count":30,"area":null},{"id":"2101.04640","title":"Dimensions of Commonsense Knowledge","created":"2021-01-12","cited_by_count":29,"area":null},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2303.07616","title":"The Life Cycle of Knowledge in Big Language Models: A Survey","created":"2023-03-14","cited_by_count":23,"area":null},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","cited_by_count":21,"area":null},{"id":"2112.13834","title":"What do Large Language Models Learn about Scripts?","created":"2021-12-27","cited_by_count":19,"area":null},{"id":"2303.07735","title":"Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models","created":"2023-03-14","cited_by_count":18,"area":"lr"},{"id":"2210.07471","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","created":"2022-10-14","cited_by_count":15,"area":null},{"id":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15,"area":"lr"},{"id":"2406.19898","title":"Paraphrase Types Elicit Prompt Engineering Capabilities","created":"2024-06-28","cited_by_count":15,"area":null},{"id":"2108.06665","title":"Accurate, yet inconsistent? Consistency Analysis on Language Understanding Models","created":"2021-08-15","cited_by_count":13,"area":null},{"id":"2109.04672","title":"Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model","created":"2021-09-10","cited_by_count":13,"area":null},{"id":"2203.08452","title":"Can Pre-trained Language Models Interpret Similes as Smart as Human?","created":"2022-03-16","cited_by_count":13,"area":null},{"id":"2210.17517","title":"Lila: A Unified Benchmark for Mathematical Reasoning","created":"2022-10-31","cited_by_count":13,"area":"lr"},{"id":"2301.11293","title":"Understanding Finetuning for Factual Knowledge Extraction from Language Models","created":"2023-01-26","cited_by_count":13,"area":null},{"id":"2204.03084","title":"Knowledge Infused Decoding","created":"2022-04-06","cited_by_count":12,"area":null},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2308.15299","title":"TaskLAMA: Probing the Complex Task Understanding of Language Models","created":"2023-08-29","cited_by_count":12,"area":null},{"id":"2108.01928","title":"How to Query Language Models?","created":"2021-08-04","cited_by_count":11,"area":null},{"id":"2302.08143","title":"Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2205.03815","title":"Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text Correspondence","created":"2022-05-08","cited_by_count":10,"area":null},{"id":"2211.12668","title":"DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data","created":"2022-11-23","cited_by_count":10,"area":null},{"id":"2305.10782","title":"Human Behavioral Benchmarking: Numeric Magnitude Comparison Effects in Large Language Models","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2409.11798","title":"The Factuality of Large Language Models in the Legal Domain","created":"2024-09-18","cited_by_count":10,"area":null},{"id":"2104.10193","title":"Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks","created":"2021-04-20","cited_by_count":9,"area":null},{"id":"2210.05159","title":"Can Language Models Be Specific? How?","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2211.00609","title":"A Simple, Yet Effective Approach to Finding Biases in Code Generation","created":"2022-10-31","cited_by_count":8,"area":null},{"id":"2310.15239","title":"CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks","created":"2023-10-23","cited_by_count":8,"area":"lr"},{"id":"2211.04281","title":"SocioProbe: What, When, and Where Language Models Learn about Sociodemographics","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2302.07926","title":"Commonsense Reasoning for Conversational AI: A Survey of the State of the Art","created":"2023-02-15","cited_by_count":7,"area":"lr"},{"id":"2305.05403","title":"Completeness, Recall, and Negation in Open-World Knowledge Bases: A Survey","created":"2023-05-09","cited_by_count":7,"area":null},{"id":"2305.10998","title":"The Web Can Be Your Oyster for Improving Large Language Models","created":"2023-05-18","cited_by_count":7,"area":null},{"id":"2401.12078","title":"Temporal Blind Spots in Large Language Models","created":"2024-01-22","cited_by_count":7,"area":null},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","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":"2204.05673","title":"What do Toothbrushes do in the Kitchen? How Transformers Think our World is Structured","created":"2022-04-12","cited_by_count":5,"area":"lr"},{"id":"2312.17055","title":"Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2108.04674","title":"Natural Language Processing with Commonsense Knowledge: A Survey","created":"2021-08-10","cited_by_count":4,"area":null},{"id":"2202.12801","title":"On the data requirements of probing","created":"2022-02-25","cited_by_count":4,"area":null},{"id":"2204.10176","title":"Probing Script Knowledge from Pre-Trained Models","created":"2022-04-16","cited_by_count":4,"area":null},{"id":"2212.00837","title":"Analogical Math Word Problems Solving with Enhanced Problem-Solution Association","created":"2022-12-01","cited_by_count":4,"area":"lr"},{"id":"2309.04635","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2312.17532","title":"Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception","created":"2023-12-29","cited_by_count":4,"area":"lr"},{"id":"2109.13123","title":"Automatic Generation of Word Problems for Academic Education via Natural Language Processing (NLP)","created":"2021-09-27","cited_by_count":3,"area":null},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","cited_by_count":3,"area":"lr"},{"id":"2312.12853","title":"CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models","created":"2023-12-20","cited_by_count":3,"area":"lr"},{"id":"2407.01047","title":"Development of Cognitive Intelligence in Pre-trained Language Models","created":"2024-07-01","cited_by_count":3,"area":null},{"id":"2204.07835","title":"What If: Generating Code to Answer Simulation Questions","created":"2022-04-16","cited_by_count":2,"area":null},{"id":"2210.06246","title":"CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm","created":"2022-10-12","cited_by_count":2,"area":"lr"},{"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":"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":"2503.23779","title":"WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization","created":"2025-03-31","cited_by_count":2,"area":"lr"},{"id":"2203.15754","title":"Evaluating Prompts Across Multiple Choice Tasks In a Zero-Shot Setting","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2206.10265","title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2210.13311","title":"Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2211.12054","title":"Visually Grounded Commonsense Knowledge Acquisition","created":"2022-11-22","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":"2402.14355","title":"Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?","created":"2024-02-22","cited_by_count":1,"area":"lr"},{"id":"2404.19432","title":"Can Large Language Models put 2 and 2 together? Probing for Entailed Arithmetical Relationships","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2507.15707","title":"Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked?","created":"2025-07-21","cited_by_count":1,"area":"lr"},{"id":"2210.14724","title":"Improving Imbalanced Text Classification with Dynamic Curriculum Learning","created":"2022-10-25","cited_by_count":0,"area":null},{"id":"2311.02237","title":"Explainable Authorship Identification in Cultural Heritage Applications: Analysis of a New Perspective","created":"2023-11-03","cited_by_count":0,"area":null}],"next_cursor":"100"}