{"total":46,"rows":[{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487,"area":null},{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192,"area":null},{"id":"2310.00656","title":"LEGO-Prover: Neural Theorem Proving with Growing Libraries","created":"2023-10-01","cited_by_count":109,"area":null},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75,"area":null},{"id":"2308.05342","title":"Metacognitive Prompting Improves Understanding in Large Language Models","created":"2023-08-10","cited_by_count":58,"area":null},{"id":"2407.00379","title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation","created":"2024-06-29","cited_by_count":49,"area":null},{"id":"2407.07064","title":"Prompting Techniques for Secure Code Generation: A Systematic Investigation","created":"2024-07-09","cited_by_count":34,"area":null},{"id":"2308.00304","title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","created":"2023-08-01","cited_by_count":33,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31,"area":null},{"id":"2509.16865","title":"Large Language Models as End-to-end Combinatorial Optimization Solvers","created":"2025-09-21","cited_by_count":28,"area":null},{"id":"2309.15806","title":"Lyra: Orchestrating Dual Correction in Automated Theorem Proving","created":"2023-09-27","cited_by_count":25,"area":null},{"id":"2507.18342","title":"EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs","created":"2025-07-24","cited_by_count":23,"area":null},{"id":"2310.14201","title":"Prompt Engineering Through the Lens of Optimal Control","created":"2023-10-22","cited_by_count":16,"area":null},{"id":"2311.11482","title":"Meta Prompting for AI Systems","created":"2023-11-20","cited_by_count":16,"area":null},{"id":"2305.19835","title":"Deliberate then Generate: Enhanced Prompting Framework for Text Generation","created":"2023-05-31","cited_by_count":13,"area":null},{"id":"2502.15359","title":"ARS: Automatic Routing Solver with Large Language Models","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2310.03331","title":"Fine-tune Language Models to Approximate Unbiased In-context Learning","created":"2023-10-05","cited_by_count":12,"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":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2310.05035","title":"Self-Convinced Prompting: Few-Shot Question Answering with Repeated Introspection","created":"2023-10-08","cited_by_count":7,"area":null},{"id":"2402.14837","title":"An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guide","created":"2024-02-18","cited_by_count":7,"area":null},{"id":"2406.12644","title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2309.13218","title":"Language Models for Business Optimisation with a Real World Case Study in Production Scheduling","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2310.14403","title":"O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2406.10878","title":"Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions","created":"2024-06-16","cited_by_count":4,"area":null},{"id":"2408.07272","title":"Abstract Operations Research Modeling Using Natural Language Inputs","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2502.12185","title":"Large Language Models for Extrapolative Modeling of Manufacturing Processes","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2507.07694","title":"SAS: Simulated Attention Score","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2304.11957","title":"Benchmarking ChatGPT-4 on ACR Radiation Oncology In-Training (TXIT) Exam and Red Journal Gray Zone Cases: Potentials and Challenges for AI-Assisted Medical Education and Decision Making in Radiation Oncology","created":"2023-04-24","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":"2602.01090","title":"Hard Constraints Meet Soft Generation: Guaranteed Feasibility for LLM-based Combinatorial Optimization","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2306.16275","title":"Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting","created":"2023-06-28","cited_by_count":2,"area":null},{"id":"2310.12960","title":"SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2410.16973","title":"Learning Mathematical Rules with Large Language Models","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2412.00798","title":"Combinatorial Rising Bandits","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2502.19973","title":"Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2510.08624","title":"Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.09230","title":"Diagnosing Shoulder Disorders Using Multimodal Large Language Models and Consumer-Grade Cameras","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.22477","title":"Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2511.00985","title":"ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2511.11576","title":"DAOpt: Modeling and Evaluation of Data-Driven Optimization under Uncertainty with LLMs","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2409.13693","title":"Declarative Integration and Management of Large Language Models through Finite Automata: Application to Automation, Communication, and Ethics","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2605.12106","title":"Large Language Models as Amortized Pareto-Front Generators for Constrained Bi-Objective Convex Optimization","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2609.11018","title":"Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.37175","title":"VLM Fine-Tuning for End-to-End Combinatorial Optimization","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}