{"total":141,"rows":[{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125,"area":null},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138,"area":null},{"id":"2310.19596","title":"LLMaAA: Making Large Language Models as Active Annotators","created":"2023-10-30","cited_by_count":79,"area":null},{"id":"2306.00176","title":"Automated Annotation with Generative AI Requires Validation","created":"2023-05-31","cited_by_count":76,"area":null},{"id":"2310.04668","title":"Label-free Node Classification on Graphs with Large Language Models (LLMS)","created":"2023-10-07","cited_by_count":72,"area":null},{"id":"2305.14871","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","created":"2023-05-24","cited_by_count":70,"area":null},{"id":"2305.14292","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","created":"2023-05-23","cited_by_count":67,"area":null},{"id":"2305.13660","title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","created":"2023-05-23","cited_by_count":61,"area":null},{"id":"2405.16043","title":"Theoretical Analysis of Weak-to-Strong Generalization","created":"2024-05-25","cited_by_count":48,"area":null},{"id":"2312.10007","title":"Faithful Persona-based Conversational Dataset Generation with Large Language Models","created":"2023-12-15","cited_by_count":47,"area":null},{"id":"2402.18050","title":"MEGAnno+: A Human-LLM Collaborative Annotation System","created":"2024-02-28","cited_by_count":47,"area":null},{"id":"2309.13340","title":"Towards LLM-guided Causal Explainability for Black-box Text Classifiers","created":"2023-09-23","cited_by_count":44,"area":null},{"id":"2308.12261","title":"Prompt2Model: Generating Deployable Models from Natural Language Instructions","created":"2023-08-23","cited_by_count":41,"area":null},{"id":"2308.01284","title":"Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?","created":"2023-08-02","cited_by_count":39,"area":null},{"id":"2402.16379","title":"TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement","created":"2024-02-26","cited_by_count":39,"area":null},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2402.16795","title":"If in a Crowdsourced Data Annotation Pipeline, a GPT-4","created":"2024-02-26","cited_by_count":38,"area":null},{"id":"2306.03090","title":"Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction","created":"2023-06-05","cited_by_count":37,"area":null},{"id":"2304.13861","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","created":"2023-04-26","cited_by_count":35,"area":null},{"id":"2309.13063","title":"Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies","created":"2023-09-14","cited_by_count":34,"area":null},{"id":"2410.15413","title":"A Comprehensive Evaluation of Cognitive Biases in LLMs","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2306.15766","title":"Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost","created":"2023-06-27","cited_by_count":33,"area":null},{"id":"2406.05374","title":"Planning Like Human: A Dual-process Framework for Dialogue Planning","created":"2024-06-08","cited_by_count":32,"area":null},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2310.17555","title":"Interactive Robot Learning from Verbal Correction","created":"2023-10-26","cited_by_count":29,"area":null},{"id":"2405.01299","title":"The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation","created":"2024-05-02","cited_by_count":29,"area":null},{"id":"2402.11073","title":"AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators","created":"2024-02-16","cited_by_count":28,"area":null},{"id":"2403.00165","title":"TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision","created":"2024-02-29","cited_by_count":25,"area":null},{"id":"2410.02657","title":"Hate Personified: Investigating the role of LLMs in content moderation","created":"2024-10-03","cited_by_count":25,"area":null},{"id":"2406.06369","title":"Annotation alignment: Comparing LLM and human annotations of conversational safety","created":"2024-06-10","cited_by_count":23,"area":null},{"id":"2404.18864","title":"Performance-Aligned LLMs for Generating Fast Code","created":"2024-04-29","cited_by_count":21,"area":null},{"id":"2305.01723","title":"Stance Detection: A Practical Guide to Classifying Political Beliefs in Text","created":"2023-05-02","cited_by_count":20,"area":null},{"id":"2410.18889","title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance","created":"2024-10-24","cited_by_count":20,"area":null},{"id":"2406.03248","title":"Large Language Models as Evaluators for Recommendation Explanations","created":"2024-06-05","cited_by_count":19,"area":null},{"id":"2403.18152","title":"Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency","created":"2024-03-26","cited_by_count":18,"area":null},{"id":"2409.09467","title":"Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI","created":"2024-09-14","cited_by_count":17,"area":null},{"id":"2310.20470","title":"Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation","created":"2023-10-31","cited_by_count":16,"area":null},{"id":"2403.12403","title":"Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales","created":"2024-03-19","cited_by_count":16,"area":null},{"id":"2404.09682","title":"Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation","created":"2024-04-15","cited_by_count":16,"area":null},{"id":"2405.11290","title":"MBIAS: Mitigating Bias in Large Language Models While Retaining Context","created":"2024-05-18","cited_by_count":15,"area":null},{"id":"2411.11081","title":"The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection","created":"2024-11-17","cited_by_count":15,"area":null},{"id":"2502.11267","title":"Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent","created":"2025-02-16","cited_by_count":15,"area":null},{"id":"2502.04362","title":"LLMs can be easily Confused by Instructional Distractions","created":"2025-02-05","cited_by_count":13,"area":null},{"id":"2401.00284","title":"Evaluation is all you need. Prompting Generative Large Language Models for Annotation Tasks in the Social Sciences. A Primer using Open Models","created":"2023-12-30","cited_by_count":12,"area":null},{"id":"2409.18857","title":"Mitigating Selection Bias with Node Pruning and Auxiliary Options","created":"2024-09-27","cited_by_count":12,"area":null},{"id":"2410.03908","title":"Still Not Quite There! Evaluating Large Language Models for Comorbid Mental Health Diagnosis","created":"2024-10-04","cited_by_count":12,"area":null},{"id":"2305.14770","title":"Using Natural Language Explanations to Rescale Human Judgments","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2402.05512","title":"GPTs Are Multilingual Annotators for Sequence Generation Tasks","created":"2024-02-08","cited_by_count":11,"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":"2305.08339","title":"Assessing the potential of LLM-assisted annotation for corpus-based pragmatics and discourse analysis: The case of apology","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2407.11004","title":"The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators","created":"2024-06-25","cited_by_count":10,"area":null},{"id":"2511.14342","title":"ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions","created":"2025-11-18","cited_by_count":10,"area":null},{"id":"2305.02626","title":"\"Oops, Did I Just Say That?\" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process","created":"2023-05-04","cited_by_count":9,"area":null},{"id":"2405.05109","title":"QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs","created":"2024-05-08","cited_by_count":9,"area":null},{"id":"2306.09343","title":"SIGHT: A Large Annotated Dataset on Student Insights Gathered from Higher Education Transcripts","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2309.06503","title":"Leveraging Large Language Models and Weak Supervision for Social Media data annotation: an evaluation using COVID-19 self-reported vaccination tweets","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2403.01774","title":"WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations","created":"2024-03-04","cited_by_count":7,"area":null},{"id":"2404.02261","title":"LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource Languages","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2405.12081","title":"Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Model","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2405.14646","title":"Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2406.11109","title":"Investigating Annotator Bias in Large Language Models for Hate Speech Detection","created":"2024-06-17","cited_by_count":6,"area":null},{"id":"2502.15980","title":"Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2308.10758","title":"DepreSym: A Depression Symptom Annotated Corpus and the Role of LLMs as Assessors of Psychological Markers","created":"2023-08-21","cited_by_count":5,"area":null},{"id":"2311.03798","title":"Noisy Pair Corrector for Dense Retrieval","created":"2023-11-07","cited_by_count":5,"area":null},{"id":"2311.09552","title":"Large Language Models are Few-Shot Training Example Generators: A Case Study in Fallacy Recognition","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2412.14276","title":"Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Data","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2502.15990","title":"Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search","created":"2025-02-21","cited_by_count":5,"area":null},{"id":"2509.11118","title":"We Argue to Agree: Towards Personality-Driven Argumentation-Based Negotiation Dialogue Systems for Tourism","created":"2025-09-14","cited_by_count":5,"area":null},{"id":"2312.07049","title":"Improving Factual Error Correction by Learning to Inject Factual Errors","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2402.08666","title":"Improving Generalization in Semantic Parsing by Increasing Natural Language Variation","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2407.11827","title":"GPT Assisted Annotation of Rhetorical and Linguistic Features for Interpretable Propaganda Technique Detection in News Text","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2409.09741","title":"Benchmarking LLMs in Political Content Text-Annotation: Proof-of-Concept with Toxicity and Incivility Data","created":"2024-09-15","cited_by_count":4,"area":null},{"id":"2410.14180","title":"XForecast: Evaluating Natural Language Explanations for Time Series Forecasting","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2410.17099","title":"Human-LLM Hybrid Text Answer Aggregation for Crowd Annotations","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2505.17795","title":"DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2507.13138","title":"Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation","created":"2025-07-17","cited_by_count":4,"area":null},{"id":"2307.11031","title":"Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2402.01783","title":"Hierarchical Multi-Label Classification of Online Vaccine Concerns","created":"2024-02-01","cited_by_count":3,"area":null},{"id":"2402.13518","title":"RITFIS: Robust input testing framework for LLMs-based intelligent software","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2406.14099","title":"Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2407.19795","title":"VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2410.03254","title":"Are Expert-Level Language Models Expert-Level Annotators?","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2509.12288","title":"Digital Voices of Survival: From Social Media Disclosures to Support Provisions for Domestic Violence Victims","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2509.24866","title":"Metaphor identification using large language models: A comparison of RAG, prompt engineering, and fine-tuning","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2510.16549","title":"ReviewGuard: Enhancing Deficient Peer Review Detection via LLM-Driven Data Augmentation","created":"2025-10-18","cited_by_count":3,"area":null},{"id":"2601.13922","title":"Automatic Prompt Optimization for Dataset-Level Feature Discovery","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2305.15070","title":"Annotation Imputation to Individualize Predictions: Initial Studies on Distribution Dynamics and Model Predictions","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2402.14428","title":"KoCoSa: Korean Context-aware Sarcasm Detection Dataset","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2405.05758","title":"Exploring the Human-LLM Synergy in Advancing Theory-driven Qualitative Analysis","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2406.14169","title":"Optimizing Novelty of Top-k Recommendations using Large Language Models and Reinforcement Learning","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2407.09003","title":"Enhancing Few-Shot Stock Trend Prediction with Large Language Models","created":"2024-07-12","cited_by_count":2,"area":null},{"id":"2407.10645","title":"Prompt Selection Matters: Enhancing Text Annotations for Social Sciences with Large Language Models","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2407.12826","title":"Assessing the Effectiveness of GPT-4o in Climate Change Evidence Synthesis and Systematic Assessments: Preliminary Insights","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2407.14346","title":"Improving Retrieval in Sponsored Search by Leveraging Query Context Signals","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2410.05573","title":"TaeBench: Improving Quality of Toxic Adversarial Examples","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2410.14074","title":"Transferring Natural Language Datasets Between Languages Using Large Language Models for Modern Decision Support and Sci-Tech Analytical Systems","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2505.13418","title":"Dementia Through Different Eyes: Explainable Modeling of Human and LLM Perceptions for Early Awareness","created":"2025-05-19","cited_by_count":2,"area":null}],"next_cursor":"100"}