{"total":66,"rows":[{"id":"2408.09235","title":"Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA","created":"2024-08-17","cited_by_count":25,"area":null},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2503.12600","title":"GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation","created":"2025-03-16","cited_by_count":17,"area":null},{"id":"2507.22168","title":"Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles","created":"2025-07-29","cited_by_count":16,"area":null},{"id":"2410.09992","title":"Evaluating Gender Bias of LLMs in Making Morality Judgements","created":"2024-10-13","cited_by_count":15,"area":null},{"id":"2504.01282","title":"Prompt-Reverse Inconsistency: LLM Self-Inconsistency Beyond Generative Randomness and Prompt Paraphrasing","created":"2025-04-02","cited_by_count":14,"area":null},{"id":"2503.22353","title":"Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions","created":"2025-03-28","cited_by_count":13,"area":null},{"id":"2411.00932","title":"LLMs: A Game-Changer for Software Engineers?","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2601.23045","title":"The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2412.15772","title":"Linguistic Features Extracted by GPT-4 Improve Alzheimer's Disease Detection based on Spontaneous Speech","created":"2024-12-20","cited_by_count":8,"area":null},{"id":"2505.21701","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2603.05651","title":"The Fragility Of Moral Judgment In Large Language Models","created":"2026-03-05","cited_by_count":8,"area":null},{"id":"2409.03735","title":"Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","cited_by_count":6,"area":null},{"id":"2411.13244","title":"Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2601.05062","title":"Compositional Steering of Large Language Models with Steering Tokens","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2502.16395","title":"AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science","created":"2025-02-23","cited_by_count":4,"area":null},{"id":"2504.21117","title":"Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2505.15101","title":"Cost-aware LLM-based Online Dataset Annotation","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2504.15022","title":"LLMs as Data Annotators: How Close Are We to Human Performance","created":"2025-04-21","cited_by_count":3,"area":null},{"id":"2511.21714","title":"GPS: General Per-Sample Prompter","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2602.04297","title":"Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2505.20120","title":"Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2509.01182","title":"Question-to-Knowledge (Q2K): Multi-Agent Generation of Inspectable Facts for Product Mapping","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2509.10414","title":"Is In-Context Learning Learning?","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2509.19590","title":"Position: AI Evaluations Should be Grounded on a Theory of Capability","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2512.11013","title":"PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2603.26539","title":"How Open Must Language Models be to Enable Reliable Scientific Inference?","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2605.30646","title":"Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.25090","title":"Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering","created":"2026-07-27","cited_by_count":2,"area":null},{"id":"2412.17189","title":"Talking with Tables for Better LLM Factual Data Interactions","created":"2024-12-22","cited_by_count":1,"area":null},{"id":"2504.20196","title":"Understanding and supporting how developers prompt for LLM-powered code editing in practice","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2507.07539","title":"CEA-LIST at CheckThat! 2025: Evaluating LLMs as Detectors of Bias and Opinion in Text","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2509.12678","title":"Instance-level Randomization: Toward More Stable LLM Evaluations","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2510.26193","title":"RCScore: Quantifying Response Consistency in Large Language Models","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2511.19956","title":"Prompt Fairness: Sub-group Disparities in LLMs","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.09444","title":"Advancing Text Classification with Large Language Models and Neural Attention Mechanisms","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2601.03493","title":"Submodular Evaluation Subset Selection in Automatic Prompt Optimization","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.16890","title":"LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2603.03298","title":"TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.21373","title":"PLR: Plackett-Luce for Reordering In-Context Learning Examples","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2603.28561","title":"Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systems","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2605.30040","title":"Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2608.07494","title":"How to Ask the AI: A User Perspective Survey for Large Language Model Prompting","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2408.11936","title":"Estimating Contribution Quality in Online Deliberations Using a Large Language Model","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2503.00992","title":"Evidence of conceptual mastery in the application of rules by Large Language Models","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2505.03053","title":"Developing A Framework to Support Human Evaluation of Bias in Generated Free Response Text","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2506.00072","title":"Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2508.06017","title":"Position: Intelligent Coding Systems Should Write Programs with Justifications","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.09303","title":"From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.10946","title":"When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2510.08388","title":"If Probable, Then Acceptable? Understanding Conditional Acceptability Judgments in Large Language Models","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2601.21618","title":"Semantic Content Determines Algorithmic Performance","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.25169","title":"To Write or to Automate Linguistic Prompts, That Is the Question","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.14672","title":"SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.21786","title":"From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2604.22207","title":"Evaluating LLM-Based Goal Extraction in Requirements Engineering: Prompting Strategies and Their Limitations","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.04665","title":"Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.03357","title":"The Unsampled Truth: Quantifying Prompt Artifacts in LM Psychometrics","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.15521","title":"Emergent retokenization symmetry in large language models: phenomenology and applications","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2607.15957","title":"From Plausible to Actionable: A Position on LLM Self-Explanations","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.10315","title":"Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.18539","title":"Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2610.01428","title":"Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15884","title":"RetryBench: Separating Retry Permission from Recovery Outcomes in GPT Tool Use","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.19084","title":"Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}