{"total":72,"rows":[{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699,"area":null},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232,"area":null},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153,"area":null},{"id":"2302.05698","title":"Compositional Exemplars for In-context Learning","created":"2023-02-11","cited_by_count":144,"area":null},{"id":"2303.08233","title":"NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions","created":"2023-03-14","cited_by_count":135,"area":null},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124,"area":null},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107,"area":null},{"id":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84,"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":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59,"area":null},{"id":"2312.13108","title":"ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation","created":"2023-12-20","cited_by_count":45,"area":null},{"id":"2106.15339","title":"SpreadsheetCoder: Formula Prediction from Semi-structured Context","created":"2021-06-26","cited_by_count":41,"area":null},{"id":"2311.09278","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","created":"2023-11-15","cited_by_count":39,"area":null},{"id":"2211.09374","title":"Execution-based Evaluation for Data Science Code Generation Models","created":"2022-11-17","cited_by_count":32,"area":null},{"id":"2302.10166","title":"Learning Deep Semantics for Test Completion","created":"2023-02-20","cited_by_count":31,"area":null},{"id":"2105.07911","title":"SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising","created":"2021-05-17","cited_by_count":27,"area":null},{"id":"2310.17894","title":"Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey","created":"2023-10-27","cited_by_count":27,"area":null},{"id":"2109.10294","title":"DeepSTL -- From English Requirements to Signal Temporal Logic","created":"2021-09-21","cited_by_count":22,"area":null},{"id":"2604.25727","title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","created":"2026-04-28","cited_by_count":22,"area":null},{"id":"2105.08928","title":"Investigating Math Word Problems using Pretrained Multilingual Language Models","created":"2021-05-19","cited_by_count":21,"area":null},{"id":"2203.07781","title":"UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL","created":"2022-03-15","cited_by_count":20,"area":null},{"id":"2301.12950","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","created":"2023-01-30","cited_by_count":20,"area":null},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2305.01528","title":"FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information","created":"2023-05-02","cited_by_count":18,"area":null},{"id":"2104.13100","title":"Shellcode_IA32: A Dataset for Automatic Shellcode Generation","created":"2021-04-27","cited_by_count":16,"area":null},{"id":"2211.05165","title":"Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database","created":"2022-11-09","cited_by_count":16,"area":null},{"id":"2405.17264","title":"On the Noise Robustness of In-Context Learning for Text Generation","created":"2024-05-27","cited_by_count":16,"area":null},{"id":"2207.13211","title":"A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialog","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2405.16450","title":"Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2407.02211","title":"PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning","created":"2024-07-02","cited_by_count":13,"area":null},{"id":"2109.02445","title":"Multi-modal Program Inference: a Marriage of Pre-trainedLanguage Models and Component-based Synthesis","created":"2021-09-03","cited_by_count":12,"area":null},{"id":"2305.13917","title":"Generating Data for Symbolic Language with Large Language Models","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2406.11925","title":"DocCGen: Document-based Controlled Code Generation","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2605.22535","title":"TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks","created":"2026-05-21","cited_by_count":10,"area":null},{"id":"2402.06733","title":"NICE: To Optimize In-Context Examples or Not?","created":"2024-02-09","cited_by_count":9,"area":null},{"id":"2406.11890","title":"Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2409.02074","title":"RACONTEUR: A Knowledgeable, Insightful, and Portable LLM-Powered Shell Command Explainer","created":"2024-09-03","cited_by_count":9,"area":null},{"id":"2307.08309","title":"LogPr\\'ecis: Unleashing Language Models for Automated Malicious Log Analysis","created":"2023-07-17","cited_by_count":8,"area":null},{"id":"2405.19581","title":"Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2103.02523","title":"NeurIPS 2020 NLC2CMD Competition: Translating Natural Language to Bash Commands","created":"2021-03-03","cited_by_count":7,"area":null},{"id":"2303.06018","title":"Hierarchical Neural Program Synthesis","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"2205.01293","title":"A Survey of Deep Learning Models for Structural Code Understanding","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2502.08576","title":"Mapping the Landscape of Generative AI in Network Monitoring and Management","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2107.02438","title":"Shell Language Processing: Unix command parsing for Machine Learning","created":"2021-07-06","cited_by_count":3,"area":null},{"id":"2202.04847","title":"A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2302.07845","title":"NL2CMD: An Updated Workflow for Natural Language to Bash Commands Translation","created":"2023-02-15","cited_by_count":3,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2409.13551","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2409.17166","title":"ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement","created":"2024-09-12","cited_by_count":3,"area":null},{"id":"2502.06858","title":"LLM-Supported Natural Language to Bash Translation","created":"2025-02-07","cited_by_count":3,"area":null},{"id":"2506.04579","title":"Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2511.17565","title":"Generative Caching for Structurally Similar Prompts and Responses","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2203.15319","title":"Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation","created":"2022-03-29","cited_by_count":2,"area":null},{"id":"2212.09132","title":"JEMMA: An Extensible Java Dataset for ML4Code Applications","created":"2022-12-18","cited_by_count":2,"area":null},{"id":"2310.13247","title":"Anomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Approaches","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2511.19422","title":"SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2606.20510","title":"Efficient and Sound Probabilistic Verification for AI Agents","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2310.05380","title":"Augmented Embeddings for Custom Retrievals","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2310.17228","title":"TST$^\\mathrm{R}$: Target Similarity Tuning Meets the Real World","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2402.18329","title":"Robust Synthetic Data-Driven Detection of Living-Off-the-Land Reverse Shells","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2608.13547","title":"QuoteBench: How Matched Scores Can Hide Command-Path Failures","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2106.14347","title":"Revelio: ML-Generated Debugging Queries for Distributed Systems","created":"2021-06-28","cited_by_count":0,"area":null},{"id":"2111.03000","title":"Reducing the impact of out of vocabulary words in the translation of natural language questions into SPARQL queries","created":"2021-11-04","cited_by_count":0,"area":null},{"id":"2202.03755","title":"Can We Generate Shellcodes via Natural Language? An Empirical Study","created":"2022-02-08","cited_by_count":0,"area":null},{"id":"2505.18374","title":"ShIOEnv: A Command Evaluation Environment for Grammar-Constrained Synthesis and Execution Behavior Modeling","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2510.01453","title":"The Command Line GUIde: Graphical Interfaces from Man Pages via AI","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2511.20677","title":"Prompt Engineering Techniques for Context-dependent Text-to-SQL in Arabic","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2607.27766","title":"Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.01611","title":"EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}