{"total":137,"rows":[{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554,"area":null},{"id":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53,"area":null},{"id":"2311.06102","title":"Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking","created":"2023-11-10","cited_by_count":37,"area":null},{"id":"2309.10954","title":"In-Context Learning for Text Classification with Many Labels","created":"2023-09-19","cited_by_count":35,"area":null},{"id":"2304.09972","title":"MasakhaNEWS: News Topic Classification for African languages","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2410.22284","title":"Embedding-based classifiers can detect prompt injection attacks","created":"2024-10-29","cited_by_count":27,"area":"safety"},{"id":"2310.14192","title":"PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2410.01627","title":"Intent Detection in the Age of LLMs","created":"2024-10-02","cited_by_count":25,"area":null},{"id":"2403.17169","title":"QuanTemp: A real-world open-domain benchmark for fact-checking numerical claims","created":"2024-03-25","cited_by_count":23,"area":null},{"id":"2405.10808","title":"ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios","created":"2024-05-17","cited_by_count":18,"area":null},{"id":"2508.07662","title":"GLiClass: Generalist Lightweight Model for Sequence Classification Tasks","created":"2025-08-11","cited_by_count":15,"area":null},{"id":"2309.17447","title":"A Large Language Model Approach to Educational Survey Feedback Analysis","created":"2023-09-29","cited_by_count":14,"area":null},{"id":"2304.01238","title":"Spam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection","created":"2023-04-03","cited_by_count":13,"area":null},{"id":"2306.05052","title":"Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models","created":"2023-06-08","cited_by_count":13,"area":null},{"id":"2307.11694","title":"SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design","created":"2023-06-19","cited_by_count":13,"area":null},{"id":"2305.12641","title":"A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2308.14634","title":"Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance","created":"2023-08-28","cited_by_count":12,"area":null},{"id":"2501.08284","title":"AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages","created":"2025-01-14","cited_by_count":11,"area":null},{"id":"2303.16028","title":"Synthetically generated text for supervised text analysis","created":"2023-03-28","cited_by_count":10,"area":null},{"id":"2502.13372","title":"MoVer: Motion Verification for Motion Graphics Animations","created":"2025-02-19","cited_by_count":10,"area":"mllm"},{"id":"2210.00471","title":"OCD: Learning to Overfit with Conditional Diffusion Models","created":"2022-10-02","cited_by_count":9,"area":"diffusion"},{"id":"2305.12576","title":"Automated Few-shot Classification with Instruction-Finetuned Language Models","created":"2023-05-21","cited_by_count":9,"area":null},{"id":"2504.01850","title":"Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming Tasks","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2302.13149","title":"STACC: Code Comment Classification using SentenceTransformers","created":"2023-02-25","cited_by_count":5,"area":null},{"id":"2303.01593","title":"QAID: Question Answering Inspired Few-shot Intent Detection","created":"2023-03-02","cited_by_count":5,"area":null},{"id":"2305.16598","title":"NormMark: A Weakly Supervised Markov Model for Socio-cultural Norm Discovery","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2403.17536","title":"ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2405.03845","title":"Self-Improving Customer Review Response Generation Based on LLMs","created":"2024-05-06","cited_by_count":5,"area":"synth"},{"id":"2501.12332","title":"Automatic Labelling with Open-source LLMs using Dynamic Label Schema Integration","created":"2025-01-21","cited_by_count":5,"area":null},{"id":"2512.12677","title":"Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches","created":"2025-12-14","cited_by_count":5,"area":null},{"id":"2402.10597","title":"Efficiency at Scale: Investigating the Performance of Diminutive Language Models in Clinical Tasks","created":"2024-02-16","cited_by_count":4,"area":null},{"id":"2603.18908","title":"Ventriloquist LLMs: Linear Alignment of Late-Stage Representations","created":"2026-03-19","cited_by_count":4,"area":null},{"id":"2605.31140","title":"EvoDefense: Co-Evolving Black-Box Defense with Large Language Models","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2212.09422","title":"Human in the loop: How to effectively create coherent topics by manually labeling only a few documents per class","created":"2022-12-19","cited_by_count":3,"area":null},{"id":"2305.13058","title":"Retrieval-augmented Multi-label Text Classification","created":"2023-05-22","cited_by_count":3,"area":"rag"},{"id":"2305.16031","title":"Efficient Document Embeddings via Self-Contrastive Bregman Divergence Learning","created":"2023-05-25","cited_by_count":3,"area":null},{"id":"2311.00408","title":"AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2311.13881","title":"A Multi-solution Study on GDPR AI-enabled Completeness Checking of DPAs","created":"2023-11-23","cited_by_count":3,"area":null},{"id":"2407.02834","title":"Aspect-Based Sentiment Analysis Techniques: A Comparative Study","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2410.05770","title":"Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2410.12858","title":"Large Language Models for Medical OSCE Assessment: A Novel Approach to Transcript Analysis","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2212.10391","title":"Empowering Sentence Encoders with Prompting and Label Retrieval for Zero-shot Text Classification","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2304.01331","title":"Creating Custom Event Data Without Dictionaries: A Bag-of-Tricks","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2305.03793","title":"Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labels","created":"2023-05-05","cited_by_count":2,"area":null},{"id":"2307.12155","title":"Identifying Misinformation on YouTube through Transcript Contextual Analysis with Transformer Models","created":"2023-07-22","cited_by_count":2,"area":null},{"id":"2310.13247","title":"Anomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Approaches","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2402.16700","title":"Generating Effective Ensembles for Sentiment Analysis","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2404.12365","title":"When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many Classes","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2405.14863","title":"A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2408.13202","title":"Instruct-DeBERTa: A Hybrid Approach for Aspect-based Sentiment Analysis on Textual Reviews","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2410.19889","title":"Ensembling Finetuned Language Models for Text Classification","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2411.04604","title":"FASSILA: A Corpus for Algerian Dialect Fake News Detection and Sentiment Analysis","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2503.11376","title":"Annotating Scientific Uncertainty: A comprehensive model using linguistic patterns and comparison with existing approaches","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2505.07672","title":"OnPrem.LLM: A Privacy-Conscious Document Intelligence Toolkit","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2506.08364","title":"Structure-Augmented Reasoning Generation","created":"2025-06-10","cited_by_count":2,"area":"lr"},{"id":"2603.18174","title":"Conflict-Free Policy Languages for Probabilistic ML Predicates: A Framework and Case Study with the Semantic Router DSL","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2605.03450","title":"Retrieving Floods without Floodlights: Topic Models as Binary Classifiers for Extreme Climate Events in German News","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2608.02089","title":"How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2212.09376","title":"Enriching Relation Extraction with OpenIE","created":"2022-12-19","cited_by_count":1,"area":null},{"id":"2303.09901","title":"mCPT at SemEval-2023 Task 3: Multilingual Label-Aware Contrastive Pre-Training of Transformers for Few- and Zero-shot Framing Detection","created":"2023-03-17","cited_by_count":1,"area":null},{"id":"2304.01890","title":"Sociocultural knowledge is needed for selection of shots in hate speech detection tasks","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2304.14179","title":"NAP at SemEval-2023 Task 3: Is Less Really More? (Back-)Translation as Data Augmentation Strategies for Detecting Persuasion Techniques","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2305.15016","title":"Estimating class separability of text embeddings with persistent homology","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2306.09752","title":"Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2309.06844","title":"Gpachov at CheckThat! 2023: A Diverse Multi-Approach Ensemble for Subjectivity Detection in News Articles","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2311.14727","title":"Optimal strategies to perform multilingual analysis of social content for a novel dataset in the tourism domain","created":"2023-11-20","cited_by_count":1,"area":null},{"id":"2401.13229","title":"From Random to Informed Data Selection: A Diversity-Based Approach to Optimize Human Annotation and Few-Shot Learning","created":"2024-01-24","cited_by_count":1,"area":null},{"id":"2402.15755","title":"Dental Severity Assessment through Few-shot Learning and SBERT Fine-tuning","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2403.02121","title":"Leveraging Weakly Annotated Data for Hate Speech Detection in Code-Mixed Hinglish: A Feasibility-Driven Transfer Learning Approach with Large Language Models","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2403.19802","title":"Developing Healthcare Language Model Embedding Spaces","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2404.03987","title":"Investigating the Robustness of Modelling Decisions for Few-Shot Cross-Topic Stance Detection: A Preregistered Study","created":"2024-04-05","cited_by_count":1,"area":null},{"id":"2409.20147","title":"Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2410.00179","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2503.17425","title":"Beyond Negation Detection: Comprehensive Assertion Detection Models for Clinical NLP","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2505.22157","title":"LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.09259","title":"Self-Anchored Attention Model for Sample-Efficient Classification of Prosocial Text Chat","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2507.04173","title":"Efficient Detection of Intermittent Job Failures Using Few-Shot Learning","created":"2025-07-05","cited_by_count":1,"area":null},{"id":"2508.20468","title":"ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.05635","title":"Few-Shot Query Intent Detection via Relation-Aware Prompt Learning","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2510.15125","title":"Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2601.22264","title":"Predicting Intermittent Job Failure Categories for Diagnosis Using Few-Shot Fine-Tuned Language Models","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.08907","title":"Cross-Domain Uncertainty Quantification for Selective Prediction: A Comprehensive Bound Ablation with Transfer-Informed Betting","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2605.02798","title":"Measuring Accuracy and Energy-to-Solution of Quantum Fine-Tuning of Foundational AI Models","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2606.08605","title":"Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2610.00346","title":"Benchmarking System One decision models against trained classifiers and language models for automated decision gates","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2303.12489","title":"Few-shot Multimodal Multitask Multilingual Learning","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2307.02882","title":"Contrast Is All You Need","created":"2023-07-06","cited_by_count":0,"area":null},{"id":"2308.09765","title":"Taken by Surprise: Contrast effect for Similarity Scores","created":"2023-08-18","cited_by_count":0,"area":null},{"id":"2309.11895","title":"Audio Contrastive-based Fine-tuning: Decoupling Representation Learning and Classification","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2309.16275","title":"UPB @ ACTI: Detecting Conspiracies using fine tuned Sentence Transformers","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2312.11020","title":"Information Type Classification with Contrastive Task-Specialized Sentence Encoders","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2401.09555","title":"Improving Classification Performance With Human Feedback: Label a few, we label the rest","created":"2024-01-17","cited_by_count":0,"area":"alignment"},{"id":"2401.14654","title":"A Korean Legal Judgment Prediction Dataset for Insurance Disputes","created":"2024-01-26","cited_by_count":0,"area":null},{"id":"2406.09206","title":"Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language Models","created":"2024-06-13","cited_by_count":0,"area":"synth"},{"id":"2407.00342","title":"KPC-cF: Aspect-Based Sentiment Analysis via Implicit-Feature Alignment with Corpus Filtering","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2407.06893","title":"Measuring Sustainability Intention of ESG Fund Disclosure using Few-Shot Learning","created":"2024-07-09","cited_by_count":0,"area":null},{"id":"2408.06930","title":"Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2408.15213","title":"Classifying populist language in American presidential and governor speeches using automatic text analysis","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2410.00427","title":"Conversational Exploratory Search of Scholarly Publications Using Knowledge Graphs","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2411.13786","title":"Adaptable Embeddings Network (AEN)","created":"2024-11-21","cited_by_count":0,"area":null}],"next_cursor":"100"}