{"total":151,"rows":[{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974,"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":"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":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119,"area":null},{"id":"2310.15123","title":"Branch-Solve-Merge Improves Large Language Model Evaluation and Generation","created":"2023-10-23","cited_by_count":106,"area":null},{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2308.15197","title":"Where Would I Go Next? Large Language Models as Human Mobility Predictors","created":"2023-08-29","cited_by_count":93,"area":null},{"id":"2307.16376","title":"When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities","created":"2023-07-31","cited_by_count":90,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2308.00675","title":"Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models","created":"2023-08-01","cited_by_count":68,"area":null},{"id":"2403.11322","title":"StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows","created":"2024-03-17","cited_by_count":65,"area":null},{"id":"2504.15257","title":"FlowReasoner: Reinforcing Query-Level Meta-Agents","created":"2025-04-21","cited_by_count":63,"area":null},{"id":"2312.03003","title":"Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation","created":"2023-12-04","cited_by_count":58,"area":null},{"id":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47,"area":null},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47,"area":null},{"id":"2401.07950","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","created":"2024-01-15","cited_by_count":39,"area":null},{"id":"2404.00492","title":"Multi-hop Question Answering under Temporal Knowledge Editing","created":"2024-03-30","cited_by_count":36,"area":null},{"id":"2405.18369","title":"PromptWizard: Task-Aware Prompt Optimization Framework","created":"2024-05-28","cited_by_count":36,"area":null},{"id":"2312.07413","title":"AI capabilities can be significantly improved without expensive retraining","created":"2023-12-12","cited_by_count":28,"area":null},{"id":"2306.09719","title":"Pushing the Limits of ChatGPT on NLP Tasks","created":"2023-06-16","cited_by_count":27,"area":null},{"id":"2310.11409","title":"LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks","created":"2023-10-17","cited_by_count":27,"area":null},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27,"area":null},{"id":"2308.01589","title":"Holy Grail 2.0: From Natural Language to Constraint Models","created":"2023-08-03","cited_by_count":26,"area":null},{"id":"2404.08126","title":"Auctions with LLM Summaries","created":"2024-04-11","cited_by_count":24,"area":null},{"id":"2405.14804","title":"Can LLMs Solve longer Math Word Problems Better?","created":"2024-05-23","cited_by_count":22,"area":null},{"id":"2603.28088","title":"GEMS: Agent-Native Multimodal Generation with Memory and Skills","created":"2026-03-30","cited_by_count":21,"area":null},{"id":"2501.19378","title":"TableMaster: A Recipe to Advance Table Understanding with Language Models","created":"2025-01-31","cited_by_count":18,"area":null},{"id":"2502.12435","title":"A Survey on Large Language Models for Automated Planning","created":"2025-02-18","cited_by_count":17,"area":null},{"id":"2306.01590","title":"Log Parsing: How Far Can ChatGPT Go?","created":"2023-06-02","cited_by_count":16,"area":null},{"id":"2401.12576","title":"LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations","created":"2024-01-23","cited_by_count":16,"area":null},{"id":"2510.23564","title":"ReCode: Unify Plan and Action for Universal Granularity Control","created":"2025-10-27","cited_by_count":15,"area":null},{"id":"2412.15249","title":"LitLLMs, LLMs for Literature Review: Are we there yet?","created":"2024-12-15","cited_by_count":14,"area":null},{"id":"2312.00819","title":"Large Language Models for Travel Behavior Prediction","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2402.16181","title":"How Can LLM Guide RL? A Value-Based Approach","created":"2024-02-25","cited_by_count":13,"area":null},{"id":"2409.17972","title":"BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search","created":"2024-09-26","cited_by_count":13,"area":null},{"id":"2506.08607","title":"Sample Efficient Demonstration Selection for In-Context Learning","created":"2025-06-10","cited_by_count":13,"area":null},{"id":"2404.00614","title":"Learning to Plan for Language Modeling from Unlabeled Data","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2405.15452","title":"Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top","created":"2024-05-24","cited_by_count":12,"area":null},{"id":"2411.02478","title":"Imagining and building wise machines: The centrality of AI metacognition","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2508.02721","title":"Blueprint First, Model Second: A Framework for Deterministic LLM Workflow","created":"2025-08-01","cited_by_count":12,"area":null},{"id":"2510.08521","title":"FlowSearch: Advancing deep research with dynamic structured knowledge flow","created":"2025-10-09","cited_by_count":10,"area":null},{"id":"2402.09546","title":"How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2504.09482","title":"HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs","created":"2025-04-13","cited_by_count":8,"area":null},{"id":"2505.02091","title":"LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications","created":"2025-05-04","cited_by_count":8,"area":null},{"id":"2406.12104","title":"End-to-end Text-to-SQL Generation within an Analytics Insight Engine","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2407.06027","title":"PAS: Data-Efficient Plug-and-Play Prompt Augmentation System","created":"2024-07-08","cited_by_count":7,"area":null},{"id":"2412.09429","title":"From Intention To Implementation: Automating Biomedical Research via LLMs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2506.03278","title":"FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2506.06950","title":"What Makes a Good Natural Language Prompt?","created":"2025-06-07","cited_by_count":7,"area":null},{"id":"2403.05468","title":"Will GPT-4 Run DOOM?","created":"2024-03-08","cited_by_count":6,"area":null},{"id":"2506.12421","title":"Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints","created":"2025-06-14","cited_by_count":6,"area":null},{"id":"2507.21108","title":"A Survey of Classification Tasks and Approaches for Legal Contracts","created":"2025-07-09","cited_by_count":6,"area":null},{"id":"2602.10525","title":"LHAW: Controllable Underspecification for Long-Horizon Tasks","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2309.12940","title":"Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models","created":"2023-09-22","cited_by_count":5,"area":null},{"id":"2503.10628","title":"Uncertainty in Action: Confidence Elicitation in Embodied Agents","created":"2025-03-13","cited_by_count":5,"area":null},{"id":"2505.15874","title":"Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2509.18487","title":"Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2601.05187","title":"SimuAgent: An LLM-Based Simulink Modeling Assistant Enhanced with Reinforcement Learning","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2309.00900","title":"Large Process Models: A Vision for Business Process Management in the Age of Generative AI","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2312.13876","title":"Capture the Flag: Uncovering Data Insights with Large Language Models","created":"2023-12-21","cited_by_count":4,"area":null},{"id":"2403.16097","title":"Can Language Models Pretend Solvers? Logic Code Simulation with LLMs","created":"2024-03-24","cited_by_count":4,"area":null},{"id":"2406.02598","title":"Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problems","created":"2024-06-01","cited_by_count":4,"area":null},{"id":"2407.12882","title":"InstructAV: Instruction Fine-tuning Large Language Models for Authorship Verification","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2409.09629","title":"Confidence Estimation for LLM-Based Dialogue State Tracking","created":"2024-09-15","cited_by_count":4,"area":null},{"id":"2412.05127","title":"The Prompt Canvas: A Literature-Based Practitioner Guide for Creating Effective Prompts in Large Language Models","created":"2024-12-06","cited_by_count":4,"area":null},{"id":"2502.16838","title":"REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2503.19007","title":"Option Discovery Using LLM-guided Semantic Hierarchical Reinforcement Learning","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2503.21602","title":"GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprise","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2510.24891","title":"Idea2Plan: Exploring AI-Powered Research Planning","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2308.10444","title":"Dynamic Strategy Chain: Dynamic Zero-Shot CoT for Long Mental Health Support Generation","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2310.18358","title":"A Communication Theory Perspective on Prompting Engineering Methods for Large Language Models","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2401.07518","title":"Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2406.10505","title":"CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding","created":"2024-06-15","cited_by_count":3,"area":null},{"id":"2502.11114","title":"Beyond Pairwise: Global Zero-shot Temporal Graph Generation","created":"2025-02-16","cited_by_count":3,"area":null},{"id":"2503.18681","title":"Commander-GPT: Fully Unleashing the Sarcasm Detection Capability of Multi-Modal Large Language Models","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2505.08446","title":"Agent-as-a-Service based on Agent Network","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2509.23836","title":"Mix-Ecom: Towards Mixed-Type E-Commerce Dialogues with Complex Domain Rules","created":"2025-09-28","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":"2512.07608","title":"Metric-Fair Prompting: Treating Similar Samples Similarly","created":"2025-12-08","cited_by_count":3,"area":null},{"id":"2602.08367","title":"WorldTravel: A Realistic Multimodal Travel-Planning Benchmark with Tightly Coupled Constraints","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2603.06213","title":"Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2404.03052","title":"GPT-DETOX: An In-Context Learning-Based Paraphraser for Text Detoxification","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2408.05566","title":"Document-Level Event Extraction with Definition-Driven ICL","created":"2024-08-10","cited_by_count":2,"area":null},{"id":"2410.15086","title":"Towards Safer Heuristics With XPlain","created":"2024-10-19","cited_by_count":2,"area":null},{"id":"2412.17332","title":"A Dual-Perspective Metaphor Detection Framework Using Large Language Models","created":"2024-12-23","cited_by_count":2,"area":null},{"id":"2504.15080","title":"Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2505.08459","title":"Strategy-Augmented Planning for Large Language Models via Opponent Exploitation","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2505.08492","title":"Achieving Scalable Robot Autonomy via neurosymbolic planning using lightweight local LLM","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2505.12257","title":"LLM Context Conditioning and PWP Prompting for Multimodal Validation of Chemical Formulas","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2506.14702","title":"Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2506.19420","title":"Commander-GPT: Dividing and Routing for Multimodal Sarcasm Detection","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2507.21099","title":"Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2511.00763","title":"A Quantitative Study of Sustained Focus in Large Language Models via Repetitive Deterministic Prediction Tasks","created":"2025-11-02","cited_by_count":2,"area":null},{"id":"2603.14382","title":"StAR: Segment Anything Reasoner","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2608.09277","title":"P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2312.14798","title":"Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases","created":"2023-12-22","cited_by_count":1,"area":null},{"id":"2401.15724","title":"RE-GAINS & EnChAnT: Intelligent Tool Manipulation Systems For Enhanced Query Responses","created":"2024-01-28","cited_by_count":1,"area":null},{"id":"2409.03844","title":"MetaBGM: Dynamic Soundtrack Transformation For Continuous Multi-Scene Experiences With Ambient Awareness And Personalization","created":"2024-09-05","cited_by_count":1,"area":null}],"next_cursor":"100"}