{"total":43,"rows":[{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737,"area":null},{"id":"2205.12689","title":"Large Language Models are Few-Shot Clinical Information Extractors","created":"2022-05-25","cited_by_count":207,"area":null},{"id":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155,"area":null},{"id":"2304.09433","title":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes","created":"2023-04-19","cited_by_count":111,"area":null},{"id":"2303.04132","title":"Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction","created":"2023-03-07","cited_by_count":89,"area":null},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86,"area":null},{"id":"2308.03279","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","created":"2023-08-07","cited_by_count":72,"area":null},{"id":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53,"area":null},{"id":"2310.13671","title":"Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models","created":"2023-10-20","cited_by_count":30,"area":null},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"id":"2404.11122","title":"Small Language Models are Good Too: An Empirical Study of Zero-Shot Classification","created":"2024-04-17","cited_by_count":18,"area":null},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14,"area":null},{"id":"2309.07601","title":"Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals","created":"2023-09-14","cited_by_count":14,"area":null},{"id":"2311.15614","title":"FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models","created":"2023-11-27","cited_by_count":14,"area":null},{"id":"2406.01306","title":"Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2410.13006","title":"LLM Chain Ensembles for Scalable and Accurate Data Annotation","created":"2024-10-16","cited_by_count":11,"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":"2305.17442","title":"Weaker Than You Think: A Critical Look at Weakly Supervised Learning","created":"2023-05-27","cited_by_count":8,"area":null},{"id":"2305.18623","title":"Alfred: A System for Prompted Weak Supervision","created":"2023-05-29","cited_by_count":8,"area":null},{"id":"2406.06723","title":"Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing","created":"2024-06-10","cited_by_count":8,"area":null},{"id":"2208.14362","title":"AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels","created":"2022-08-30","cited_by_count":7,"area":null},{"id":"2305.13723","title":"PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2312.04601","title":"Weak Supervision Performance Evaluation via Partial Identification","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2303.16445","title":"Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2502.12366","title":"ScriptoriumWS: A Code Generation Assistant for Weak Supervision","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2403.03334","title":"DIVERSE: A Dataset of YouTube Video Comment Stances with a Data Programming Model","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2407.14180","title":"Automatic Classification of News Subjects in Broadcast News: Application to a Gender Bias Representation Analysis","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2601.15690","title":"From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2306.01658","title":"An Adaptive Method for Weak Supervision with Drifting Data","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2402.01867","title":"Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2402.06056","title":"ActiveDP: Bridging Active Learning and Data Programming","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2403.15430","title":"Distilling Named Entity Recognition Models for Endangered Species from Large Language Models","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2406.11010","title":"WeShap: Weak Supervision Source Evaluation with Shapley Values","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2410.15051","title":"Automatic identification of diagnosis from hospital discharge letters via weakly supervised Natural Language Processing","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2505.20880","title":"MSA at SemEval-2025 Task 3: High Quality Weak Labeling and LLM Ensemble Verification for Multilingual Hallucination Detection","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2604.08578","title":"Structured Exploration and Exploitation of Label Functions for Automated Data Annotation","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2210.08677","title":"Regularized Data Programming with Automated Bayesian Prior Selection","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2306.02859","title":"Local Boosting for Weakly-Supervised Learning","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2502.05923","title":"ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2604.24179","title":"MemeScouts@LT-EDI 2026: Asking the Right Questions -- Prompted Weak Supervision for Meme Hate Speech Detection","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2607.01293","title":"RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.16507","title":"Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2610.07708","title":"Evidence Before Sampling: Interpretable Implicit Negative Candidate Discovery for Recommendation","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}