{"total":46,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120,"area":null},{"id":"2210.10109","title":"A Survey of Active Learning for Natural Language Processing","created":"2022-10-18","cited_by_count":40,"area":null},{"id":"2210.12391","title":"MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition","created":"2022-10-22","cited_by_count":38,"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":"2102.05486","title":"Towards More Fine-grained and Reliable NLP Performance Prediction","created":"2021-02-10","cited_by_count":26,"area":null},{"id":"2103.07792","title":"Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling","created":"2021-03-13","cited_by_count":25,"area":null},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2409.18472","title":"URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base","created":"2024-09-27","cited_by_count":21,"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":"2209.05948","title":"Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems","created":"2022-09-13","cited_by_count":13,"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":"2212.01757","title":"Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer","created":"2022-12-04","cited_by_count":11,"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":"2501.14491","title":"Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter","created":"2025-01-24","cited_by_count":10,"area":null},{"id":"2402.01865","title":"What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2501.01558","title":"Predicting the Performance of Black-box LLMs through Follow-up Queries","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2105.14115","title":"Towards More Equitable Question Answering Systems: How Much More Data Do You Need?","created":"2021-05-28","cited_by_count":8,"area":null},{"id":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2210.11255","title":"Evidence > Intuition: Transferability Estimation for Encoder Selection","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2405.11125","title":"A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base","created":"2024-05-17","cited_by_count":7,"area":null},{"id":"2410.16710","title":"Influential Language Data Selection via Gradient Trajectory Pursuit","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2101.07086","title":"Model Compression for Domain Adaptation through Causal Effect Estimation","created":"2021-01-18","cited_by_count":6,"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":"2205.00953","title":"BERTops: Studying BERT Representations under a Topological Lens","created":"2022-05-02","cited_by_count":5,"area":null},{"id":"2209.07351","title":"Rethinking Round-Trip Translation for Machine Translation Evaluation","created":"2022-09-15","cited_by_count":4,"area":null},{"id":"2201.05017","title":"Towards Automated Error Analysis: Learning to Characterize Errors","created":"2022-01-13","cited_by_count":3,"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":"2510.19217","title":"Modality Matching Matters: Calibrating Language Distances for Cross-Lingual Transfer in URIEL+","created":"2025-10-22","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":"2505.20264","title":"We Need to Measure Data Diversity in NLP -- Better and Broader","created":"2025-05-26","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":"2310.17166","title":"X-SNS: Cross-Lingual Transfer Prediction through Sub-Network Similarity","created":"2023-10-26","cited_by_count":0,"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":"2510.09519","title":"Can We Reliably Rank Model Performance across Domains without Labeled Data?","created":"2025-10-10","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},{"id":"2609.03775","title":"Typological Feature Prediction with Large Language Models: An In-Context Learning Approach","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.32331","title":"Language Distances are Practical for Equitable Cross-Lingual Transfer","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}