{"total":89,"rows":[{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557,"area":"synth"},{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244,"area":"synth"},{"id":"2305.13971","title":"Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning","created":"2023-05-23","cited_by_count":197,"area":null},{"id":"2312.17617","title":"Large Language Models for Generative Information Extraction: A Survey","created":"2023-12-29","cited_by_count":185,"area":null},{"id":"2303.08559","title":"Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!","created":"2023-03-15","cited_by_count":119,"area":null},{"id":"2308.06374","title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges","created":"2023-08-11","cited_by_count":71,"area":null},{"id":"2405.19716","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","created":"2024-05-30","cited_by_count":70,"area":"mllm"},{"id":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63,"area":"alignment"},{"id":"2410.02603","title":"Agents' Room: Narrative Generation through Multi-step Collaboration","created":"2024-10-03","cited_by_count":57,"area":"agents"},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2305.15041","title":"Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science","created":"2023-05-24","cited_by_count":37,"area":"synth"},{"id":"2311.01270","title":"People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection","created":"2023-11-02","cited_by_count":25,"area":null},{"id":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"id":"2307.14712","title":"Evaluating Generative Models for Graph-to-Text Generation","created":"2023-07-27","cited_by_count":16,"area":null},{"id":"2311.08921","title":"Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models","created":"2023-11-15","cited_by_count":15,"area":"synth"},{"id":"2305.14970","title":"Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning","created":"2023-05-24","cited_by_count":13,"area":"lr"},{"id":"2404.04293","title":"Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding","created":"2024-04-04","cited_by_count":12,"area":"lr"},{"id":"2502.19557","title":"Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?","created":"2025-02-26","cited_by_count":12,"area":"lr"},{"id":"2402.08005","title":"Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMs","created":"2024-02-12","cited_by_count":10,"area":"alignment"},{"id":"2410.22316","title":"Understanding Synthetic Context Extension via Retrieval Heads","created":"2024-10-29","cited_by_count":10,"area":"rag"},{"id":"2504.19276","title":"Anyprefer: An Agentic Framework for Preference Data Synthesis","created":"2025-04-27","cited_by_count":10,"area":"agents"},{"id":"2401.09967","title":"Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access","created":"2024-01-18","cited_by_count":9,"area":null},{"id":"2403.00794","title":"Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models","created":"2024-02-23","cited_by_count":9,"area":null},{"id":"2411.03250","title":"DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models","created":"2024-11-05","cited_by_count":9,"area":"diffusion"},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2601.08198","title":"Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs","created":"2026-01-13","cited_by_count":9,"area":"synth"},{"id":"2406.07188","title":"Merging Improves Self-Critique Against Jailbreak Attacks","created":"2024-06-11","cited_by_count":8,"area":"safety"},{"id":"2402.08073","title":"Grounding Data Science Code Generation with Input-Output Specifications","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2403.02586","title":"Improving Event Definition Following For Zero-Shot Event Detection","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2410.08393","title":"The Effects of Hallucinations in Synthetic Training Data for Relation Extraction","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2305.15090","title":"STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2502.18702","title":"A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition","created":"2025-02-25","cited_by_count":6,"area":"agents"},{"id":"2506.19773","title":"Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study","created":"2025-06-24","cited_by_count":6,"area":null},{"id":"2512.00590","title":"Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models","created":"2025-11-29","cited_by_count":6,"area":null},{"id":"2305.01901","title":"Few-shot Event Detection: An Empirical Study and a Unified View","created":"2023-05-03","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":"2502.17328","title":"Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2509.02040","title":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","created":"2025-09-02","cited_by_count":5,"area":"synth"},{"id":"2310.09725","title":"KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2403.15214","title":"InstaSynth: Opportunities and Challenges in Generating Synthetic Instagram Data with ChatGPT for Sponsored Content Detection","created":"2024-03-22","cited_by_count":4,"area":null},{"id":"2406.10258","title":"Curating Grounded Synthetic Data with Global Perspectives for Equitable AI","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2406.17305","title":"Retrieval Augmented Instruction Tuning for Open NER with Large Language Models","created":"2024-06-25","cited_by_count":4,"area":"rag"},{"id":"2411.13045","title":"Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning","created":"2024-11-20","cited_by_count":4,"area":"distill"},{"id":"2502.00808","title":"Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications","created":"2025-02-02","cited_by_count":4,"area":"synth"},{"id":"2506.00649","title":"GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction","created":"2025-05-31","cited_by_count":4,"area":"synth"},{"id":"2507.21340","title":"StructText: A Synthetic Table-to-Text Approach for Benchmark Generation with Multi-Dimensional Evaluation","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2510.06652","title":"Aligning Large Language Models via Fully Self-Synthetic Data","created":"2025-10-08","cited_by_count":4,"area":"alignment"},{"id":"2409.07088","title":"Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2502.17394","title":"SNaRe: Domain-aware Data Generation for Low-Resource Event Detection","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2512.14562","title":"Polypersona: Persona-Grounded LLM for Synthetic Survey Responses","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2607.01977","title":"OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models","created":"2026-07-02","cited_by_count":3,"area":null},{"id":"2308.07645","title":"Steering Language Generation: Harnessing Contrastive Expert Guidance and Negative Prompting for Coherent and Diverse Synthetic Data Generation","created":"2023-08-15","cited_by_count":2,"area":"synth"},{"id":"2508.05474","title":"Can Large Language Models Generate Effective Datasets for Emotion Recognition in Conversations?","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2510.02133","title":"FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2512.05066","title":"Multi-LLM Collaboration for Medication Recommendation","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2309.06550","title":"Synthetic Text Generation using Hypergraph Representations","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2311.06364","title":"Relation Extraction in underexplored biomedical domains: A diversity-optimised sampling and synthetic data generation approach","created":"2023-11-10","cited_by_count":1,"area":"synth"},{"id":"2403.11103","title":"ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models","created":"2024-03-17","cited_by_count":1,"area":null},{"id":"2403.14562","title":"Agentic AI: The Era of Semantic Decoding","created":"2024-03-21","cited_by_count":1,"area":"agents"},{"id":"2404.03428","title":"Edisum: Summarizing and Explaining Wikipedia Edits at Scale","created":"2024-04-04","cited_by_count":1,"area":null},{"id":"2407.14371","title":"Open Artificial Knowledge","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2505.03025","title":"A Typology of Synthetic Datasets for Dialogue Processing in Clinical Contexts","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2507.05997","title":"DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2511.03610","title":"A systematic review of relation extraction task since the emergence of Transformers","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2601.19667","title":"SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2604.17803","title":"Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2606.00282","title":"Synthetic Data from Cross-Domain Events for Large-Scale Recommendation Systems","created":"2026-05-29","cited_by_count":1,"area":"synth"},{"id":"2402.16200","title":"IR2: Information Regularization for Information Retrieval","created":"2024-02-25","cited_by_count":0,"area":null},{"id":"2411.12752","title":"A Library Perspective on Supervised Text Processing in Digital Libraries: An Investigation in the Biomedical Domain","created":"2024-11-06","cited_by_count":0,"area":null},{"id":"2501.06577","title":"Survey Transfer Learning: Recycling Data with Silicon Responses","created":"2025-01-11","cited_by_count":0,"area":null},{"id":"2501.07815","title":"Agent-Centric Projection of Prompting Techniques and Implications for Synthetic Training Data for Large Language Models","created":"2025-01-14","cited_by_count":0,"area":"agents"},{"id":"2503.05620","title":"Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2505.02858","title":"Towards High-Fidelity Synthetic Multi-platform Social Media Datasets via Large Language Models","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2506.14901","title":"Combining Constrained and Unconstrained Decoding via Boosting: BoostCD and Its Application to Information Extraction","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2506.16348","title":"DISCIE -- Discriminative Closed Information Extraction","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2507.03617","title":"EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2509.01387","title":"ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Links","created":"2025-09-01","cited_by_count":0,"area":"synth"},{"id":"2511.03407","title":"Overcoming the Generalization Limits of SLM Finetuning for Shape-Based Extraction of Datatype and Object Properties","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2601.03130","title":"Automatic Prompt Engineering with No Task Cues and No Tuning","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.07152","title":"Agents of Diffusion: Enhancing Diffusion Language Models with Multi-Agent Reinforcement Learning for Structured Data Generation (Extended Version)","created":"2026-01-12","cited_by_count":0,"area":"agents"},{"id":"2602.20966","title":"Blackbird Language Matrices: A Framework to Investigate the Linguistic Competence of Language Models","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2602.23312","title":"Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.25227","title":"Comparing Natural and Synthetic Structured Data: A Study of the Passive Verb Alternation in French and Italian","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.07147","title":"Dynamic Context Evolution for Scalable Synthetic Data Generation","created":"2026-04-08","cited_by_count":0,"area":"synth"},{"id":"2604.25920","title":"Analysing Lightweight Large Language Models for Biomedical Named Entity Recognition on Diverse Ouput Formats","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2606.24734","title":"Task Decomposition for Efficient Annotation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.26807","title":"KARLA: Knowledge-base Augmented Retrieval for Language Models","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.22924","title":"Layering Virtual Try-On","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.25681","title":"Cognivia: A Cognitive Behavioral Therapy Copilot for Evidence-Based Mental Healthcare","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}