{"total":200,"rows":[{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141,"area":null},{"id":"2312.17617","title":"Large Language Models for Generative Information Extraction: A Survey","created":"2023-12-29","cited_by_count":185,"area":null},{"id":"2403.06988","title":"Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation","created":"2024-02-07","cited_by_count":101,"area":null},{"id":"2501.10868","title":"JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models","created":"2025-01-18","cited_by_count":71,"area":null},{"id":"2310.16340","title":"RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models","created":"2023-10-25","cited_by_count":65,"area":"agents"},{"id":"2402.06147","title":"DeAL: Decoding-time Alignment for Large Language Models","created":"2024-02-05","cited_by_count":55,"area":"alignment"},{"id":"2405.09605","title":"Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models","created":"2024-05-15","cited_by_count":55,"area":"wm"},{"id":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46,"area":null},{"id":"2502.05111","title":"Flexible and Efficient Grammar-Constrained Decoding","created":"2025-02-07","cited_by_count":43,"area":null},{"id":"2504.09246","title":"Type-Constrained Code Generation with Language Models","created":"2025-04-12","cited_by_count":35,"area":null},{"id":"2512.23738","title":"Enforcing Temporal Constraints for LLM Agents","created":"2025-12-25","cited_by_count":34,"area":"agents"},{"id":"2506.13752","title":"Steering LLM Thinking with Budget Guidance","created":"2025-06-16","cited_by_count":33,"area":"lr"},{"id":"2405.21068","title":"Code Pretraining Improves Entity Tracking Abilities of Language Models","created":"2024-05-31","cited_by_count":31,"area":null},{"id":"2412.03719","title":"From Language Models over Tokens to Language Models over Characters","created":"2024-12-04","cited_by_count":31,"area":null},{"id":"2406.13892","title":"Adaptable Logical Control for Large Language Models","created":"2024-06-19","cited_by_count":30,"area":null},{"id":"2504.04365","title":"AutoPDL: Automatic Prompt Optimization for LLM Agents","created":"2025-04-06","cited_by_count":27,"area":"agents"},{"id":"2504.05410","title":"Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2505.12025","title":"Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering","created":"2025-05-17","cited_by_count":21,"area":null},{"id":"2409.04267","title":"An overview of domain-specific foundation model: key technologies, applications and challenges","created":"2024-09-06","cited_by_count":19,"area":null},{"id":"2502.14905","title":"Think Inside the JSON: Reinforcement Strategy for Strict LLM Schema Adherence","created":"2025-02-18","cited_by_count":16,"area":"lr"},{"id":"2505.23061","title":"DINGO: Constrained Inference for Diffusion LLMs","created":"2025-05-29","cited_by_count":16,"area":null},{"id":"2504.07081","title":"Self-Steering Language Models","created":"2025-04-09","cited_by_count":13,"area":"lr"},{"id":"2510.03574","title":"Efficient Test-Time Scaling for Small Vision-Language Models","created":"2025-10-03","cited_by_count":12,"area":"lr"},{"id":"2410.13111","title":"Controllable Generation via Locally Constrained Resampling","created":"2024-10-17","cited_by_count":11,"area":null},{"id":"2401.14447","title":"Wordflow: Social Prompt Engineering for Large Language Models","created":"2024-01-25","cited_by_count":9,"area":null},{"id":"2408.04820","title":"Natural Language Outlines for Code: Literate Programming in the LLM Era","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2402.17988","title":"Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2402.18734","title":"Priority Sampling of Large Language Models for Compilers","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2406.13161","title":"APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts","created":"2024-06-19","cited_by_count":8,"area":null},{"id":"2606.01926","title":"Mitigating Bias in Locally Constrained Decoding via Tractable Proposals","created":"2026-06-01","cited_by_count":8,"area":null},{"id":"2606.17182","title":"Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems","created":"2026-06-15","cited_by_count":8,"area":"agents"},{"id":"2406.11403","title":"Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2602.01381","title":"On the Power of (Approximate) Reward Models for Inference-Time Scaling","created":"2026-02-01","cited_by_count":7,"area":"lr"},{"id":"2603.03305","title":"The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding","created":"2026-02-08","cited_by_count":7,"area":null},{"id":"2609.23886","title":"this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent","created":"2026-09-20","cited_by_count":7,"area":null},{"id":"2308.07791","title":"Informed Named Entity Recognition Decoding for Generative Language Models","created":"2023-08-15","cited_by_count":6,"area":null},{"id":"2408.12022","title":"Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2602.10480","title":"Neuro-Symbolic Synergy for World Modeling","created":"2026-02-11","cited_by_count":6,"area":"wm"},{"id":"2603.26285","title":"PhysVid: Physics Aware Local Conditioning for Generative Video Models","created":"2026-03-27","cited_by_count":6,"area":null},{"id":"2509.01082","title":"RefineStat: Efficient Exploration for Probabilistic Program Synthesis","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2509.01728","title":"Constrained Decoding for Safe Robot Navigation Foundation Models","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2601.07525","title":"Thinking Before Constraining: A Unified Decoding Framework for Large Language Models","created":"2026-01-12","cited_by_count":5,"area":"lr"},{"id":"2603.05193","title":"Transducing Language Models","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2505.01954","title":"Semantic Probabilistic Control of Language Models","created":"2025-05-04","cited_by_count":4,"area":null},{"id":"2602.19633","title":"TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents","created":"2026-02-23","cited_by_count":4,"area":"agents"},{"id":"2604.05150","title":"Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2605.07342","title":"Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2605.26128","title":"The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2607.07026","title":"Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata","created":"2026-07-08","cited_by_count":4,"area":"diffusion"},{"id":"2607.11346","title":"Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents","created":"2026-07-13","cited_by_count":4,"area":"agents"},{"id":"2608.23651","title":"Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail","created":"2026-08-24","cited_by_count":4,"area":"agents"},{"id":"2405.20245","title":"Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use","created":"2024-05-30","cited_by_count":3,"area":"rag"},{"id":"2503.02650","title":"The Effectiveness of Large Language Models in Transforming Unstructured Text to Standardized Formats","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2506.09701","title":"ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Search","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2506.13593","title":"Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2511.05578","title":"UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2512.00319","title":"RL-Struct: A Lightweight Reinforcement Learning Framework for Reliable Structured Output in LLMs","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2601.13922","title":"Automatic Prompt Optimization for Dataset-Level Feature Discovery","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2602.18773","title":"LAMMI-Pathology: A Tool-Centric Bottom-Up LVLM-Agent Framework for Molecularly Informed Medical Intelligence in Pathology","created":"2026-02-21","cited_by_count":3,"area":"agents"},{"id":"2603.00846","title":"Tiny-Critic RAG: Empowering Agentic Fallback with Parameter-Efficient Small Language Models","created":"2026-03-01","cited_by_count":3,"area":"rag"},{"id":"2604.00555","title":"Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2604.03616","title":"The Format Tax","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2604.25359","title":"The Structured Output Benchmark: A Multi-Source Benchmark for Evaluating Structured Output Quality in Large Language Models","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2606.00825","title":"SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2607.20709","title":"NVIDIA-labs OO Agents: Native Python Object-Oriented Agents","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2609.32160","title":"Typed Decision Models: An Early Evidence Audit and Evaluation Checklist","created":"2026-09-26","cited_by_count":3,"area":null},{"id":"2408.04392","title":"Open-domain Implicit Format Control for Large Language Model Generation","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2410.09206","title":"pyhgf: A neural network library for predictive coding","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2502.00032","title":"Querying Databases with Function Calling","created":"2025-01-23","cited_by_count":2,"area":"agents"},{"id":"2506.05128","title":"DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning","created":"2025-06-05","cited_by_count":2,"area":"lr"},{"id":"2508.03665","title":"A DbC Inspired Neurosymbolic Layer for Trustworthy Agent Design","created":"2025-08-05","cited_by_count":2,"area":"agents"},{"id":"2510.09211","title":"DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction","created":"2025-10-10","cited_by_count":2,"area":"lr"},{"id":"2512.05439","title":"BEAVER: An Efficient Deterministic LLM Verifier","created":"2025-12-05","cited_by_count":2,"area":null},{"id":"2512.06991","title":"Prompting-in-a-Series: Psychology-Informed Contents and Embeddings for Personality Recognition With Decoder-Only Models","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2601.10254","title":"NoReGeo: Non-Reasoning Geometry Benchmark","created":"2026-01-15","cited_by_count":2,"area":"lr"},{"id":"2603.00030","title":"SimpleTool: Parallel Decoding for Real-Time LLM Function Calling","created":"2026-02-04","cited_by_count":2,"area":"agents"},{"id":"2604.11943","title":"ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2605.07698","title":"Future Validity is the Missing Statistic: From Impossibility to $\\Phi$-Estimation for Grammar-Faithful Speculative Decoding","created":"2026-05-08","cited_by_count":2,"area":"inference"},{"id":"2605.08737","title":"The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs","created":"2026-05-09","cited_by_count":2,"area":"distill"},{"id":"2605.14113","title":"ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic Workflows","created":"2026-05-13","cited_by_count":2,"area":"agents"},{"id":"2605.17626","title":"Verifier-Guided Code Translation via Meta-Step Decoding","created":"2026-05-17","cited_by_count":2,"area":"lr"},{"id":"2606.20205","title":"Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2608.01000","title":"Judging Is Not Enumerating: Silent Omissions in LLM-Authored Acceptable Sets","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2501.08421","title":"SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models","created":"2025-01-14","cited_by_count":1,"area":null},{"id":"2510.14885","title":"You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction","created":"2025-10-16","cited_by_count":1,"area":"mllm"},{"id":"2510.17883","title":"From Flows to Words: Can Zero-/Few-Shot LLMs Detect Network Intrusions? A Grammar-Constrained, Calibrated Evaluation on UNSW-NB15","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2511.15886","title":"What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning","created":"2025-11-19","cited_by_count":1,"area":"lr"},{"id":"2601.01714","title":"Entropy-Aligned Decoding of LMs for Better Writing and Reasoning","created":"2026-01-05","cited_by_count":1,"area":"lr"},{"id":"2603.05540","title":"Attention Meets Reachability: Structural Equivalence and Efficiency in Grammar-Constrained LLM Decoding","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.19790","title":"Geometric Risk Control for Vision-Language Model OCR","created":"2026-03-20","cited_by_count":1,"area":"mllm"},{"id":"2604.06066","title":"From Hallucination to Structure Snowballing: The Alignment Tax of Constrained Decoding in LLM Reflection","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2604.09494","title":"RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2604.13006","title":"One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.16870","title":"Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives","created":"2026-04-18","cited_by_count":1,"area":"agents"},{"id":"2604.18170","title":"Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing","created":"2026-04-20","cited_by_count":1,"area":"inference"},{"id":"2605.02363","title":"When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.13076","title":"TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.21765","title":"Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.00722","title":"EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models","created":"2026-05-30","cited_by_count":1,"area":"diffusion"},{"id":"2606.01513","title":"Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense","created":"2026-06-01","cited_by_count":1,"area":"safety"}],"next_cursor":"100"}