{"total":19,"rows":[{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172,"area":null},{"id":"2305.06984","title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","created":"2023-05-11","cited_by_count":111,"area":null},{"id":"2202.07654","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2310.02567","title":"Improving Automatic VQA Evaluation Using Large Language Models","created":"2023-10-04","cited_by_count":37,"area":null},{"id":"2402.11161","title":"PEDANTS: Cheap but Effective and Interpretable Answer Equivalence","created":"2024-02-17","cited_by_count":31,"area":null},{"id":"2204.11677","title":"Conversational Question Answering on Heterogeneous Sources","created":"2022-04-25","cited_by_count":26,"area":null},{"id":"2401.04695","title":"Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers","created":"2024-01-09","cited_by_count":18,"area":null},{"id":"2405.16702","title":"Accurate and Nuanced Open-QA Evaluation Through Textual Entailment","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2110.08544","title":"Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Framework","created":"2021-10-16","cited_by_count":11,"area":null},{"id":"2407.12543","title":"Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2204.10206","title":"Benchmarking Answer Verification Methods for Question Answering-Based Summarization Evaluation Metrics","created":"2022-04-21","cited_by_count":2,"area":null},{"id":"2404.15650","title":"Return of EM: Entity-driven Answer Set Expansion for QA Evaluation","created":"2024-04-24","cited_by_count":2,"area":null},{"id":"2206.12664","title":"Evaluation of Semantic Answer Similarity Metrics","created":"2022-06-25","cited_by_count":1,"area":null},{"id":"2210.05038","title":"Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks","created":"2022-10-10","cited_by_count":1,"area":null},{"id":"2305.14750","title":"Mastering the ABCDs of Complex Questions: Answer-Based Claim Decomposition for Fine-grained Self-Evaluation","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2309.12250","title":"SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2202.13581","title":"'Tis but Thy Name: Semantic Question Answering Evaluation with 11M Names for 1M Entities","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2401.13170","title":"CFMatch: Aligning Automated Answer Equivalence Evaluation with Expert Judgments For Open-Domain Question Answering","created":"2024-01-24","cited_by_count":0,"area":null},{"id":"2609.15745","title":"Look Before You Leap: Factual Decoding with Internal Attribution Signals","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}