{"total":32,"rows":[{"id":"2412.08821","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","created":"2024-12-11","cited_by_count":89,"area":null},{"id":"2506.03902","title":"The Harmonic Structure of Information Contours","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2506.01840","title":"Minimal Pair-Based Evaluation of Code-Switching","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2602.13237","title":"NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models","created":"2026-01-29","cited_by_count":5,"area":null},{"id":"2502.07352","title":"Bridging the Evaluation Gap: Leveraging Large Language Models for Topic Model Evaluation","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2411.12728","title":"Information Theory of Meaningful Communication","created":"2024-11-19","cited_by_count":3,"area":null},{"id":"2506.01846","title":"Code-Switching and Syntax: A Large-Scale Experiment","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2512.13884","title":"FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition","created":"2025-12-15","cited_by_count":3,"area":null},{"id":"2601.04350","title":"RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2603.04592","title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2508.03292","title":"Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2509.07142","title":"Toward Purpose-oriented Topic Model Evaluation enabled by Large Language Models","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2512.24517","title":"Paragraph Segmentation Revisited: Towards a Standard Task for Structuring Speech","created":"2025-12-30","cited_by_count":2,"area":null},{"id":"2603.25489","title":"Translation Asymmetry in LLMs as a Data Augmentation Factor: A Case Study for 6 Romansh Language Varieties","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2503.22973","title":"XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2605.06276","title":"Linear Semantic Segmentation for Low-Resource Spoken Dialects","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.08025","title":"Arabic Sentence Segmentation Across Genres and Punctuation Conditions","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2608.09765","title":"REFRAMED: Towards Realistic Audio Description Generation for Movies","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2502.19784","title":"NaijaNLP: A Survey of Nigerian Low-Resource Languages","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2503.07179","title":"Strategies for political-statement segmentation and labelling in unstructured text","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2510.00890","title":"Span-level Detection of AI-generated Scientific Text via Contrastive Learning and Structural Calibration","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2512.14652","title":"Segmental Attention Decoding With Long Form Acoustic Encodings","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2512.24410","title":"Comparing Approaches to Automatic Summarization in Less-Resourced Languages","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2602.18346","title":"Vichara: Appellate Judgment Prediction and Explanation for the Indian Judicial System","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2605.25263","title":"Mimir: Large-scale Multilingual Concept Modeling","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.20369","title":"CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.23621","title":"GEMCo: A Validated, Ethically Releasable Proxy for Inaccessible Counselling Data","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.18661","title":"X2Streaming-TTS: Causal Token-Level Text-to-Speech from Streaming Text with Speech-State Inheritance","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.26118","title":"ElementCheck: Complexity-Aware Long-Form Text Factuality Evaluation via Sentence Elements","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.07185","title":"SIFTING: A Novel LLM-Based Framework for Structured and Transparent Information Extraction from Clinical Free-Text Reports, with Application to Tumor Staging in Lung Cancer","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.22081","title":"Structuring occupational accident narratives for cross-sector safety analysis: Transferability of accident-process role classification","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.30121","title":"What, When, and How: Audio Description as Constrained Global Optimization","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}