{"total":51,"rows":[{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2405.09798","title":"Many-Shot In-Context Learning in Multimodal Foundation Models","created":"2024-05-16","cited_by_count":67,"area":null},{"id":"2308.12060","title":"FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering","created":"2023-08-23","cited_by_count":51,"area":null},{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2308.16361","title":"Large Language Models as Data Preprocessors","created":"2023-08-30","cited_by_count":34,"area":null},{"id":"2402.11597","title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","created":"2024-02-18","cited_by_count":30,"area":null},{"id":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2405.03547","title":"Position: Leverage Foundational Models for Black-Box Optimization","created":"2024-05-06","cited_by_count":21,"area":null},{"id":"2409.05001","title":"A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement","created":"2024-09-08","cited_by_count":21,"area":null},{"id":"2312.01678","title":"Jellyfish: A Large Language Model for Data Preprocessing","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2309.00384","title":"BatchPrompt: Accomplish more with less","created":"2023-09-01","cited_by_count":16,"area":null},{"id":"2312.03987","title":"Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration","created":"2023-12-07","cited_by_count":15,"area":null},{"id":"2402.06598","title":"CigaR: Cost-efficient Program Repair with LLMs","created":"2024-02-09","cited_by_count":15,"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":"2402.14833","title":"CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness","created":"2024-02-17","cited_by_count":12,"area":null},{"id":"2609.27678","title":"Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding","created":"2026-09-23","cited_by_count":11,"area":null},{"id":"2402.17717","title":"AmbigNLG: Addressing Task Ambiguity in Instruction for NLG","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2411.03883","title":"MEG: Medical Knowledge-Augmented Large Language Models for Question Answering","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2305.11862","title":"Reducing Sequence Length by Predicting Edit Operations with Large Language Models","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2406.10786","title":"Evaluating LLMs with Multiple Problems at once","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2505.09027","title":"Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation","created":"2025-05-13","cited_by_count":5,"area":null},{"id":"2510.10138","title":"Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2511.19830","title":"Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2408.00884","title":"Hybrid Querying Over Relational Databases and Large Language Models","created":"2024-08-01","cited_by_count":3,"area":null},{"id":"2410.01724","title":"Auto-Demo Prompting: Leveraging Generated Outputs as Demonstrations for Enhanced Batch Prompting","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2410.12444","title":"Augmenting Compliance-Guaranteed Customer Service Chatbots: Context-Aware Knowledge Expansion with Large Language Models","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2502.18791","title":"Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2403.11468","title":"CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2403.13835","title":"SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2503.03266","title":"LexGenie: Automated Generation of Structured Reports for European Court of Human Rights Case Law","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2503.15551","title":"Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack","created":"2025-03-18","cited_by_count":2,"area":null},{"id":"2506.19897","title":"Can LLMs Replace Humans During Code Chunking?","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2509.21732","title":"How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2603.22608","title":"Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2410.18701","title":"BATON: Enhancing Batch-wise Inference Efficiency for Large Language Models via Dynamic Re-batching","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2412.10587","title":"Evaluation of GPT-4o and GPT-4o-mini's Vision Capabilities for Compositional Analysis from Dried Solution Drops","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2509.00303","title":"Access Paths for Efficient Ordering with Large Language Models","created":"2025-08-30","cited_by_count":1,"area":null},{"id":"2607.23597","title":"HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework","created":"2026-07-26","cited_by_count":1,"area":null},{"id":"2608.27038","title":"Cascaded Batch Prompting","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2511.12010","title":"Leveraging Large Language Models for Career Mobility Analysis: A Study of Gender, Race, and Job Change Using U.S. Online Resume Profiles","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2604.17512","title":"ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.23255","title":"Scalable LLM-based Coding of Dialogue in Healthcare Simulation: Balancing Coding Performance, Processing Time, and Environmental Impact","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2604.26351","title":"A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2606.00285","title":"Model-Based Quality Assessment for Massively Multilingual Parallel Data","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.08617","title":"Cross-Source Reasoning-based Correction for Author Name Disambiguation","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.21098","title":"LLM-Based Multi-Reference Evaluation for Efficient and Robust Assessment of Phrase Break Annotations","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2608.14737","title":"Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.10810","title":"Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.22620","title":"Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.35250","title":"SCBO: Semantically Coherent Batching and Ordering for LLM-Based Social Surveys","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35824","title":"Reliable but Design-Sensitive: Instrument Uncertainty in LLM Annotation","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}