{"total":15,"rows":[{"id":"2502.19400","title":"TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2411.05049","title":"ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding","created":"2024-11-07","cited_by_count":15,"area":null},{"id":"2409.00113","title":"Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options","created":"2024-08-27","cited_by_count":11,"area":null},{"id":"2502.20309","title":"EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2511.17808","title":"PoETa v2: Toward More Robust Evaluation of Large Language Models in Portuguese","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2602.00279","title":"Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QA","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2605.30504","title":"Auditing LLM Benchmarks with Item Response Theory","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2505.10013","title":"DIF: A Framework for Benchmarking and Verifying Implicit Bias in LLMs","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2504.13439","title":"D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Model","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2506.11007","title":"Impact of Comments on LLM Comprehension of Legacy Code","created":"2025-04-23","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":"2607.06648","title":"Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2506.03592","title":"From Understanding to Generation: An Efficient Shortcut for Evaluating Language Models","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2510.22500","title":"Towards Scalable Oversight via Partitioned Human Supervision","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2609.13556","title":"Domain-Specific Jargon in Large Language Models: A Comparative Analysis between General-Purpose and Specialist Models","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}