{"total":159,"rows":[{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2210.06280","title":"Language Models are Realistic Tabular Data Generators","created":"2022-10-12","cited_by_count":294,"area":null},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"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":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"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":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123,"area":null},{"id":"2105.02584","title":"TABBIE: Pretrained Representations of Tabular Data","created":"2021-05-06","cited_by_count":111,"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":"2103.13136","title":"Representing Numbers in NLP: a Survey and a Vision","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68,"area":"lr"},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59,"area":null},{"id":"2305.09696","title":"Generative Table Pre-training Empowers Models for Tabular Prediction","created":"2023-05-16","cited_by_count":55,"area":null},{"id":"2105.02343","title":"CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints","created":"2021-05-05","cited_by_count":49,"area":null},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45,"area":"lr"},{"id":"2102.04110","title":"Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration","created":"2021-02-08","cited_by_count":44,"area":null},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42,"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":"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":"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":"2104.01785","title":"Annotating Columns with Pre-trained Language Models","created":"2021-04-05","cited_by_count":37,"area":null},{"id":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"area":null},{"id":"2102.02723","title":"Data-to-text Generation with Macro Planning","created":"2021-02-04","cited_by_count":34,"area":null},{"id":"2502.06533","title":"Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning","created":"2025-02-10","cited_by_count":34,"area":"lr"},{"id":"2101.08333","title":"Zero-shot Generalization in Dialog State Tracking through Generative Question Answering","created":"2021-01-20","cited_by_count":33,"area":null},{"id":"2602.19313","title":"TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics","created":"2026-02-22","cited_by_count":33,"area":"alignment"},{"id":"2107.13435","title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","created":"2021-07-28","cited_by_count":32,"area":null},{"id":"2410.11781","title":"Language Models Encode Numbers Using Digit Representations in Base 10","created":"2024-10-15","cited_by_count":32,"area":null},{"id":"2310.14029","title":"LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions","created":"2023-10-21","cited_by_count":29,"area":null},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"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":"2311.16842","title":"RELIC: Investigating Large Language Model Responses using Self-Consistency","created":"2023-11-28","cited_by_count":23,"area":"lr"},{"id":"2401.03910","title":"A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates","created":"2024-01-08","cited_by_count":23,"area":null},{"id":"2305.14824","title":"Mitigating Temporal Misalignment by Discarding Outdated Facts","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2401.03735","title":"Language Models Encode the Value of Numbers Linearly","created":"2024-01-08","cited_by_count":20,"area":"mechinterp"},{"id":"2305.14057","title":"Can Language Models Understand Physical Concepts?","created":"2023-05-23","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":"2108.06743","title":"Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning","created":"2021-08-15","cited_by_count":17,"area":null},{"id":"2110.01113","title":"Probing Language Models for Understanding of Temporal Expressions","created":"2021-10-03","cited_by_count":16,"area":null},{"id":"2201.01770","title":"NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-task Financial Forecasting","created":"2022-01-05","cited_by_count":16,"area":null},{"id":"2109.03137","title":"NumGPT: Improving Numeracy Ability of Generative Pre-trained Models","created":"2021-09-07","cited_by_count":15,"area":null},{"id":"2304.10977","title":"Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition","created":"2023-04-21","cited_by_count":15,"area":null},{"id":"2503.19114","title":"Understanding and Improving Information Preservation in Prompt Compression for LLMs","created":"2025-03-24","cited_by_count":15,"area":"inference"},{"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":"2406.04619","title":"CTSyn: A Foundation Model for Cross Tabular Data Generation","created":"2024-06-07","cited_by_count":14,"area":"diffusion"},{"id":"2502.11075","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","created":"2025-02-16","cited_by_count":14,"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":"2411.02083","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","created":"2024-11-04","cited_by_count":13,"area":null},{"id":"2502.15343","title":"Tokenization is Sensitive to Language Variation","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2105.00813","title":"Transformers: \"The End of History\" for NLP?","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2306.01707","title":"Learning Multi-Step Reasoning by Solving Arithmetic Tasks","created":"2023-06-02","cited_by_count":12,"area":"lr"},{"id":"2308.01154","title":"Arithmetic with Language Models: from Memorization to Computation","created":"2023-08-02","cited_by_count":12,"area":null},{"id":"2503.17726","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2104.07307","title":"NT5?! Training T5 to Perform Numerical Reasoning","created":"2021-04-15","cited_by_count":11,"area":null},{"id":"2108.01928","title":"How to Query Language Models?","created":"2021-08-04","cited_by_count":11,"area":null},{"id":"2209.03182","title":"On the Effectiveness of Compact Biomedical Transformers","created":"2022-09-07","cited_by_count":11,"area":"distill"},{"id":"2406.01895","title":"Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks","created":"2024-06-04","cited_by_count":11,"area":"lr"},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","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":"2207.12571","title":"Innovations in Neural Data-to-text Generation: A Survey","created":"2022-07-25","cited_by_count":10,"area":null},{"id":"2208.11445","title":"Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models","created":"2022-08-24","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":"2410.13194","title":"The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces","created":"2024-10-17","cited_by_count":10,"area":"lr"},{"id":"2104.03969","title":"Detecting of a Patient's Condition From Clinical Narratives Using Natural Language Representation","created":"2021-04-08","cited_by_count":8,"area":null},{"id":"2310.11628","title":"Learn Your Tokens: Word-Pooled Tokenization for Language Modeling","created":"2023-10-17","cited_by_count":8,"area":null},{"id":"2210.05075","title":"Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems","created":"2022-10-11","cited_by_count":7,"area":"lr"},{"id":"2507.20859","title":"Leveraging Open-Source Large Language Models for Clinical Information Extraction in Resource-Constrained Settings","created":"2025-07-28","cited_by_count":7,"area":null},{"id":"2602.07812","title":"LLMs Know More About Numbers than They Can Say","created":"2026-02-08","cited_by_count":7,"area":null},{"id":"2111.15512","title":"What Do You See in this Patient? Behavioral Testing of Clinical NLP Models","created":"2021-11-30","cited_by_count":6,"area":null},{"id":"2112.00800","title":"Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text","created":"2021-12-01","cited_by_count":6,"area":null},{"id":"2211.07455","title":"Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2311.08662","title":"Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets","created":"2023-11-15","cited_by_count":6,"area":null},{"id":"2402.01375","title":"Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization","created":"2024-02-02","cited_by_count":6,"area":null},{"id":"2601.21340","title":"EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generation","created":"2026-01-29","cited_by_count":6,"area":"rag"},{"id":"2603.02913","title":"Eliciting Numerical Predictive Distributions of LLMs Without Autoregression","created":"2026-03-03","cited_by_count":6,"area":null},{"id":"2109.09105","title":"What BERT Based Language Models Learn in Spoken Transcripts: An Empirical Study","created":"2021-09-19","cited_by_count":5,"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":"2303.14920","title":"Adapting Pretrained Language Models for Solving Tabular Prediction Problems in the Electronic Health Record","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2305.08246","title":"Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency","created":"2023-05-14","cited_by_count":5,"area":"lr"},{"id":"2407.00894","title":"How to Leverage Digit Embeddings to Represent Numbers?","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2410.04503","title":"LRHP: Learning Representations for Human Preferences via Preference Pairs","created":"2024-10-06","cited_by_count":5,"area":"alignment"},{"id":"2410.19353","title":"Interleaving Text and Number Embeddings to Solve Mathemathics Problems","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2111.10756","title":"TraVLR: Now You See It, Now You Don't! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning","created":"2021-11-21","cited_by_count":4,"area":null},{"id":"2112.06109","title":"Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models","created":"2021-12-12","cited_by_count":4,"area":null},{"id":"2209.01174","title":"Extend and Explain: Interpreting Very Long Language Models","created":"2022-09-02","cited_by_count":4,"area":null},{"id":"2211.02098","title":"Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic","created":"2022-11-03","cited_by_count":4,"area":null},{"id":"2112.02333","title":"LoNLI: An Extensible Framework for Testing Diverse Logical Reasoning Capabilities for NLI","created":"2021-12-04","cited_by_count":3,"area":null},{"id":"2205.06733","title":"Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2206.15428","title":"Test2Vec: An Execution Trace Embedding for Test Case Prioritization","created":"2022-06-28","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":"2210.12206","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2210.12302","title":"What do Large Language Models Learn beyond Language?","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2509.06806","title":"MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining","created":"2025-09-08","cited_by_count":3,"area":"lr"}],"next_cursor":"100"}