{"total":89,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487,"area":null},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2311.16079","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","created":"2023-11-27","cited_by_count":274,"area":null},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2402.14811","title":"Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking","created":"2024-02-22","cited_by_count":149,"area":null},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"area":null},{"id":"2307.14430","title":"Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models","created":"2023-07-26","cited_by_count":121,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2211.13892","title":"Complementary Explanations for Effective In-Context Learning","created":"2022-11-25","cited_by_count":71,"area":null},{"id":"2210.12810","title":"Code4Struct: Code Generation for Few-Shot Event Structure Prediction","created":"2022-10-23","cited_by_count":70,"area":null},{"id":"2305.05711","title":"CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors","created":"2023-05-09","cited_by_count":68,"area":null},{"id":"2408.10914","title":"To Code, or Not To Code? Exploring Impact of Code in Pre-training","created":"2024-08-20","cited_by_count":47,"area":null},{"id":"2403.01131","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","created":"2024-03-02","cited_by_count":45,"area":null},{"id":"2305.02363","title":"Entity Tracking in Language Models","created":"2023-05-03","cited_by_count":44,"area":null},{"id":"2405.21068","title":"Code Pretraining Improves Entity Tracking Abilities of Language Models","created":"2024-05-31","cited_by_count":31,"area":null},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"area":null},{"id":"2304.09048","title":"CodeKGC: Code Language Model for Generative Knowledge Graph Construction","created":"2023-04-18","cited_by_count":28,"area":null},{"id":"2311.07811","title":"In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax","created":"2023-11-13","cited_by_count":22,"area":null},{"id":"2305.13073","title":"Text-to-SQL Error Correction with Language Models of Code","created":"2023-05-22","cited_by_count":21,"area":null},{"id":"2309.04316","title":"Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2308.14391","title":"FIRE: Food Image to REcipe generation","created":"2023-08-28","cited_by_count":18,"area":null},{"id":"2404.01856","title":"Poro 34B and the Blessing of Multilinguality","created":"2024-04-02","cited_by_count":18,"area":null},{"id":"2410.13394","title":"Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs","created":"2024-10-17","cited_by_count":18,"area":null},{"id":"2412.09879","title":"On the Limit of Language Models as Planning Formalizers","created":"2024-12-13","cited_by_count":18,"area":null},{"id":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2307.03539","title":"Large Language Models as Batteries-Included Zero-Shot ESCO Skills Matchers","created":"2023-07-07","cited_by_count":15,"area":null},{"id":"2311.09862","title":"Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Models","created":"2023-11-16","cited_by_count":15,"area":null},{"id":"2305.11790","title":"Prompting with Pseudo-Code Instructions","created":"2023-05-19","cited_by_count":14,"area":null},{"id":"2307.08220","title":"FRANC: A Lightweight Framework for High-Quality Code Generation","created":"2023-07-17","cited_by_count":14,"area":null},{"id":"2302.08672","title":"Multimodal Subtask Graph Generation from Instructional Videos","created":"2023-02-17","cited_by_count":13,"area":null},{"id":"2308.15299","title":"TaskLAMA: Probing the Complex Task Understanding of Language Models","created":"2023-08-29","cited_by_count":12,"area":null},{"id":"2310.17050","title":"Exploring Question Decomposition for Zero-Shot VQA","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2306.04347","title":"World Models for Math Story Problems","created":"2023-06-07","cited_by_count":11,"area":null},{"id":"2310.15777","title":"MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain Applications","created":"2023-10-24","cited_by_count":11,"area":null},{"id":"2410.10083","title":"Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?","created":"2024-10-14","cited_by_count":11,"area":null},{"id":"2311.09519","title":"Leveraging Code to Improve In-context Learning for Semantic Parsing","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2408.09070","title":"CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts","created":"2024-08-17","cited_by_count":10,"area":null},{"id":"2212.10754","title":"CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding","created":"2022-12-21","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2405.05455","title":"Automated Program Repair: Emerging trends pose and expose problems for benchmarks","created":"2024-05-08","cited_by_count":7,"area":null},{"id":"2406.12000","title":"Look Further Ahead: Testing the Limits of GPT-4 in Path Planning","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2506.14276","title":"Don't throw the baby out with the bathwater: How and why deep learning for ARC","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2606.16707","title":"User as Code: Executable Memory for Personalized Agents","created":"2026-06-15","cited_by_count":7,"area":null},{"id":"2304.13250","title":"Exploring the Curious Case of Code Prompts","created":"2023-04-26","cited_by_count":6,"area":null},{"id":"2312.02249","title":"Recursive Visual Programming","created":"2023-12-04","cited_by_count":6,"area":null},{"id":"2510.21131","title":"Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2312.14215","title":"SimLM: Can Language Models Infer Parameters of Physical Systems?","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2409.02326","title":"Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining","created":"2024-09-03","cited_by_count":5,"area":null},{"id":"2410.02783","title":"Enhancing Mental Health Support through Human-AI Collaboration: Toward Secure and Empathetic AI-enabled chatbots","created":"2024-09-17","cited_by_count":5,"area":null},{"id":"2305.14874","title":"From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2305.19472","title":"PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2506.01796","title":"Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2212.05773","title":"A Survey on Natural Language Processing for Programming","created":"2022-12-12","cited_by_count":3,"area":null},{"id":"2305.14973","title":"OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2311.09601","title":"Code Models are Zero-shot Precondition Reasoners","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2407.15718","title":"Integrating AI Tutors in a Programming Course","created":"2024-07-14","cited_by_count":3,"area":null},{"id":"2503.01896","title":"Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2511.20892","title":"Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2303.08697","title":"Mirror: A Natural Language Interface for Data Querying, Summarization, and Visualization","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2304.13867","title":"Transferring Procedural Knowledge across Commonsense Tasks","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2402.16431","title":"RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2402.17377","title":"KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue Benchmark","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2403.00990","title":"Formulation Comparison for Timeline Construction using LLMs","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2403.08802","title":"Governance of Generative Artificial Intelligence for Companies","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2406.19545","title":"Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2411.03964","title":"What Really is Commonsense Knowledge?","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2501.18816","title":"Large Language Models as Common-Sense Heuristics","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2402.11821","title":"Microstructures and Accuracy of Graph Recall by Large Language Models","created":"2024-02-19","cited_by_count":1,"area":null},{"id":"2409.14880","title":"End-to-End Graph Flattening Method for Large Language Models","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2502.17909","title":"FactFlow: Automatic Fact Sheet Generation and Customization from Tabular Dataset via AI Chain Design & Implementation","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2506.08422","title":"Transforming Expert Knowledge into Scalable Ontology via Large Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2507.02846","title":"Legal Requirements Translation from Law","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2308.00624","title":"JIANG: Chinese Open Foundation Language Model","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2311.04711","title":"Training CLIP models on Data from Scientific Papers","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2409.14368","title":"Evaluating the Quality of Code Comments Generated by Large Language Models for Novice Programmers","created":"2024-09-22","cited_by_count":0,"area":null},{"id":"2411.01807","title":"Can Language Models Enable In-Context Database?","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2502.08904","title":"MIH-TCCT: Mitigating Inconsistent Hallucinations in LLMs via Event-Driven Text-Code Cyclic Training","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2503.18760","title":"Synthetic Function Demonstrations Improve Generation in Low-Resource Programming Languages","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2506.00242","title":"Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2601.07430","title":"KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.12983","title":"ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2604.00239","title":"A Taxonomy of Programming Languages for Code Generation","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.22601","title":"From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2608.18083","title":"Entity tracking emerges in sub-billion parameter language models and exceeds human performance in naturalistic narratives","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":null}