{"total":52,"rows":[{"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":"2502.05111","title":"Flexible and Efficient Grammar-Constrained Decoding","created":"2025-02-07","cited_by_count":43,"area":null},{"id":"2408.08656","title":"LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs","created":"2024-08-16","cited_by_count":25,"area":null},{"id":"2408.11061","title":"StructuredRAG: JSON Response Formatting with Large Language Models","created":"2024-08-07","cited_by_count":22,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2505.04016","title":"SLOT: Structuring the Output of Large Language Models","created":"2025-05-06","cited_by_count":18,"area":null},{"id":"2506.05754","title":"Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective","created":"2025-06-06","cited_by_count":14,"area":null},{"id":"2505.22169","title":"ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2409.18216","title":"MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2505.20645","title":"STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2510.11586","title":"Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2502.01683","title":"LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2507.05517","title":"Empowering Healthcare Practitioners with Language Models: Structuring Speech Transcripts in Two Real-World Clinical Applications","created":"2025-07-07","cited_by_count":7,"area":null},{"id":"2409.18594","title":"\"Oh LLM, I'm Asking Thee, Please Give Me a Decision Tree\": Zero-Shot Decision Tree Induction and Embedding with Large Language Models","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2411.00852","title":"EF-LLM: Energy Forecasting LLM with AI-assisted Automation, Enhanced Sparse Prediction, Hallucination Detection","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2509.21791","title":"Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inference","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2503.11858","title":"OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2505.07155","title":"Reassessing Large Language Model Boolean Query Generation for Systematic Reviews","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2509.19358","title":"Benchmarking and Improving LLM Robustness for Personalized Generation","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2409.03346","title":"Sketch: A Toolkit for Streamlining LLM Operations","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2502.12516","title":"Can LLMs Extract Frame-Semantic Arguments?","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2505.01485","title":"CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Code","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2510.01902","title":"Constrained Adaptive Rejection Sampling","created":"2025-10-02","cited_by_count":3,"area":null},{"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":"2506.03009","title":"Conditioning Large Language Models on Legal Systems? Detecting Punishable Hate Speech","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.10093","title":"Leveraging LLMs for Mission Planning in Precision Agriculture","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2508.15910","title":"Evaluating Structured Decoding for Text-to-Table Generation: Evidence from Three Datasets","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2510.00276","title":"SafePassage: High-Fidelity Information Extraction with Black Box LLMs","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2512.14805","title":"Sharing State Between Prompts and Programs","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2606.08572","title":"OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2608.08254","title":"Your Prompt Is Not the Only Prompt: How Much Do LLMs Weight Structured-Output Schema Descriptions?","created":"2026-08-08","cited_by_count":2,"area":null},{"id":"2507.01810","title":"Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2507.04623","title":"Hierarchical Intent-guided Optimization with Pluggable LLM-Driven Semantics for Session-based Recommendation","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2602.06384","title":"FMBench: Adaptive Large Language Model Output Formatting","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.08872","title":"Large Language Models for Geolocation Extraction in Humanitarian Crisis Response","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2602.16481","title":"Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.08851","title":"Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2506.13188","title":"SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2509.12866","title":"Leveraging Large Language Models to Effectively Generate Visual Data for Canine Musculoskeletal Diagnoses","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2603.01243","title":"Suffix-Constrained Greedy Search Algorithms for Causal Language Models","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2606.09004","title":"LATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended Version)","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.00601","title":"\"Don't Say It!\": Constraints, Compliance, and Communication when Language Models Play Taboo","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.22683","title":"Imprompt: A Language Framework for Prompt Programming","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.01598","title":"PICTURE: Enhancing Theory-of-Mind in Large Language Models by Revealing, Not Hiding, Characters' Lack of Knowledge","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.18409","title":"Improving Natural-Language Combinatorial-Optimization Accuracy in Resource-Constrained Language Models via Formal Abstractions","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.22229","title":"Grounded Normative Rule Generation with Structured Search","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.22249","title":"A Tutorial on Prompt Engineering: From Messy Thoughts to AI Workflows","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.27822","title":"What Confidence Routing Is Actually Doing: Auditing Routing, Calibration, and Commitment in Multi-Agent Deliberation","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2610.02001","title":"Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05094","title":"How Much Do LLM-as-a-Judge Design Choices Matter? A Systematic Comparison of Prompt Designs, Rating Scales, and Models","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.13287","title":"Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered Study","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16191","title":"Correct Choices, Failed Sequences: Choice2Seq Benchmarks Correctness Retention Across Output Interfaces","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}