{"total":44,"rows":[{"id":"2503.01622","title":"DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2502.04295","title":"Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization","created":"2025-02-06","cited_by_count":16,"area":null},{"id":"2506.19806","title":"LLM-Based Social Simulations Require a Boundary","created":"2025-06-24","cited_by_count":12,"area":null},{"id":"2510.11905","title":"LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2604.14090","title":"From Weights to Activations: Is Steering the Next Frontier of Adaptation?","created":"2026-04-15","cited_by_count":8,"area":null},{"id":"2511.21695","title":"EvalCards: A Framework for Standardized Evaluation Reporting","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2504.03048","title":"LLM Library Learning Fails: A LEGO-Prover Case Study","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2504.03975","title":"GREATERPROMPT: A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Optimization","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2505.12938","title":"Leveraging LLM Inconsistency to Boost Pass@k Performance","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2510.14242","title":"Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2604.18389","title":"Understanding the Prompt Sensitivity","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2508.21452","title":"From Canonical to Complex: Benchmarking LLM Capabilities in Undergraduate Thermodynamics","created":"2025-08-29","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":"2605.27440","title":"Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2509.17096","title":"Prompt-with-Me: in-IDE Structured Prompt Management for LLM-Driven Software Engineering","created":"2025-09-21","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":"2512.15979","title":"OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering","created":"2025-12-17","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":"2605.06937","title":"A Reproducible Optimisation Protocol for Calibrating Prompt-Based Large Language Model Workflows in Evidence Synthesis","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2608.23411","title":"STONIC: A Layered Measurement Contract for LLM Value Profiling","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2411.10813","title":"Information Anxiety in Large Language Models","created":"2024-11-16","cited_by_count":0,"area":null},{"id":"2508.07975","title":"Improving Document Retrieval Coherence for Semantically Equivalent Queries","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2512.17738","title":"When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Content","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2602.03358","title":"GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.11179","title":"From Instruction to Output: The Role of Prompting in Modern NLG","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.11674","title":"Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.10477","title":"PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses","created":"2026-03-11","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":"2605.29678","title":"Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.22797","title":"Measuring Behavior Portability in Large Language Models","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.09665","title":"Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2607.20558","title":"StabilityBench: Benchmarking Instability in LLMs","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.21547","title":"The Boundaries of Automation: A Theory of Persistent Human Participation","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.03810","title":"VIBE: A VAD-Informed Benchmark for Entity-Centered Affective Profiling of Large Language Model Outputs","created":"2026-08-04","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":"2609.01217","title":"Prompt-Robust Language Models: Which Training Strategies Work?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.16517","title":"Competence-Preserving Resume Perturbations Expose Presentation Sensitivity in LLM Screening","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.38406","title":"Evaluating Whether LLMs Can Reliably Connect the DOTs?","created":"2026-09-29","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":"2610.05278","title":"When Verifiable Counts Depend on Wording: Auditing Wording Robustness in Instruction Following","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.12718","title":"A Distributional Framework for Behavioral Characterization and Risk Management of Large Language Models","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}