{"total":22,"rows":[{"id":"2410.20245","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","created":"2024-10-26","cited_by_count":21,"area":null},{"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":"2407.06946","title":"Self-Recognition in Language Models","created":"2024-07-09","cited_by_count":18,"area":null},{"id":"2409.18857","title":"Mitigating Selection Bias with Node Pruning and Auxiliary Options","created":"2024-09-27","cited_by_count":12,"area":null},{"id":"2506.00643","title":"SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questions","created":"2025-05-31","cited_by_count":9,"area":null},{"id":"2510.00628","title":"Hearing the Order: Investigating Position Bias in Large Audio-Language Models","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2503.13771","title":"Towards AI-assisted Academic Writing","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2507.14913","title":"PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation","created":"2025-07-20","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":"2506.22232","title":"Leveraging In-Context Learning for Political Bias Testing of LLMs","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2511.21709","title":"Quantifying and Mitigating Selection Bias in LLMs: A Transferable LoRA Fine-Tuning and Efficient Majority Voting Approach","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2502.04997","title":"Aligning Black-box Language Models with Human Judgments","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2509.20278","title":"Quantifying LLM Biases Across Instruction Boundary in Mixed Question Forms","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2511.21860","title":"Improving Score Reliability of Multiple Choice Benchmarks with Consistency Evaluation and Altered Answer Choices","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2602.12445","title":"RBCorr: Response Bias Correction in Language Models","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2605.01846","title":"Do Large Language Models Plan Answer Positions? Position Bias in Multiple-Choice Question Generation","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2606.12250","title":"Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance?","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2609.04582","title":"When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2502.04037","title":"Exploring Imbalanced Annotations for Effective In-Context Learning","created":"2025-02-06","cited_by_count":0,"area":null},{"id":"2503.16674","title":"Through the LLM Looking Glass: A Socratic Probing of Donkeys, Elephants, and Markets","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2507.15581","title":"Metric assessment protocol in the context of answer fluctuation on MCQ tasks","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2610.19021","title":"Can LLMs Access their World Knowledge for Event Prediction?","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}