{"total":25,"rows":[{"id":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50,"area":null},{"id":"2109.06352","title":"Uncertainty-Aware Machine Translation Evaluation","created":"2021-09-13","cited_by_count":35,"area":null},{"id":"2305.14947","title":"How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench","created":"2023-05-24","cited_by_count":34,"area":null},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2205.06130","title":"Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models","created":"2022-05-12","cited_by_count":20,"area":null},{"id":"2406.09334","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","created":"2024-06-13","cited_by_count":20,"area":null},{"id":"2210.07352","title":"Predicting Fine-Tuning Performance with Probing","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2503.03862","title":"Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2205.06356","title":"Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2306.01015","title":"How to Estimate Model Transferability of Pre-Trained Speech Models?","created":"2023-06-01","cited_by_count":10,"area":null},{"id":"2204.06546","title":"Disentangling Uncertainty in Machine Translation Evaluation","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2210.11255","title":"Evidence > Intuition: Transferability Estimation for Encoder Selection","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2210.06725","title":"Assessing Out-of-Domain Language Model Performance from Few Examples","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2202.10408","title":"Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference","created":"2022-02-21","cited_by_count":5,"area":null},{"id":"2310.14909","title":"Linking Surface Facts to Large-Scale Knowledge Graphs","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2104.04434","title":"Larger-Context Tagging: When and Why Does It Work?","created":"2021-04-09","cited_by_count":4,"area":null},{"id":"2205.02129","title":"Are All the Datasets in Benchmark Necessary? A Pilot Study of Dataset Evaluation for Text Classification","created":"2022-05-04","cited_by_count":3,"area":null},{"id":"2204.09259","title":"DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2206.04935","title":"Sort by Structure: Language Model Ranking as Dependency Probing","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2211.05015","title":"Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2509.20645","title":"Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2510.16743","title":"Zero-Shot Performance Prediction for Probabilistic Scaling Laws","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2305.17127","title":"Characterizing and Measuring Linguistic Dataset Drift","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2403.12413","title":"Third-Party Language Model Performance Prediction from Instruction","created":"2024-03-19","cited_by_count":0,"area":null},{"id":"2605.17234","title":"Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning","created":"2026-05-17","cited_by_count":0,"area":null}],"next_cursor":null}