{"total":166,"rows":[{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"area":"moe"},{"id":"2310.10501","title":"NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails","created":"2023-10-16","cited_by_count":365,"area":null},{"id":"2507.05257","title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","created":"2025-07-07","cited_by_count":254,"area":"agents"},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146,"area":null},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2405.00200","title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","created":"2024-04-30","cited_by_count":128,"area":null},{"id":"2306.04140","title":"Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions","created":"2023-06-07","cited_by_count":125,"area":null},{"id":"2410.02694","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","created":"2024-10-03","cited_by_count":125,"area":null},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"area":null},{"id":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84,"area":null},{"id":"2212.10947","title":"Parallel Context Windows for Large Language Models","created":"2022-12-21","cited_by_count":81,"area":null},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2509.25911","title":"Mem-{\\alpha}: Learning Memory Construction via Reinforcement Learning","created":"2025-09-30","cited_by_count":55,"area":"lr"},{"id":"2204.01959","title":"Data Augmentation for Intent Classification with Off-the-shelf Large Language Models","created":"2022-04-05","cited_by_count":49,"area":null},{"id":"2109.06349","title":"Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning","created":"2021-09-13","cited_by_count":46,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2105.07316","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","created":"2021-05-15","cited_by_count":43,"area":null},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2305.12947","title":"ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness","created":"2023-05-22","cited_by_count":41,"area":null},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2107.10137","title":"Improved Text Classification via Contrastive Adversarial Training","created":"2021-07-21","cited_by_count":38,"area":null},{"id":"2104.08524","title":"Multilingual and Cross-Lingual Intent Detection from Spoken Data","created":"2021-04-17","cited_by_count":35,"area":null},{"id":"2212.10525","title":"SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks","created":"2022-12-20","cited_by_count":35,"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":"2209.06664","title":"SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation","created":"2022-09-14","cited_by_count":34,"area":null},{"id":"2401.15422","title":"A Survey on Data Augmentation in Large Model Era","created":"2024-01-27","cited_by_count":31,"area":"diffusion"},{"id":"2305.02468","title":"Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System","created":"2023-05-04","cited_by_count":30,"area":null},{"id":"2209.06638","title":"SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding","created":"2022-09-14","cited_by_count":28,"area":null},{"id":"2107.14586","title":"An Efficient DP-SGD Mechanism for Large Scale NLP Models","created":"2021-07-14","cited_by_count":27,"area":null},{"id":"2109.05782","title":"Effectiveness of Pre-training for Few-shot Intent Classification","created":"2021-09-13","cited_by_count":27,"area":null},{"id":"2409.11884","title":"Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances","created":"2024-09-18","cited_by_count":26,"area":null},{"id":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26,"area":null},{"id":"2109.10126","title":"ConvFiT: Conversational Fine-Tuning of Pretrained Language Models","created":"2021-09-21","cited_by_count":25,"area":null},{"id":"2302.05096","title":"Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information","created":"2023-02-10","cited_by_count":24,"area":null},{"id":"2201.13405","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","created":"2022-01-31","cited_by_count":23,"area":null},{"id":"2307.10172","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","created":"2023-07-19","cited_by_count":22,"area":null},{"id":"2110.08552","title":"Virtual Augmentation Supported Contrastive Learning of Sentence Representations","created":"2021-10-16","cited_by_count":21,"area":null},{"id":"2203.13920","title":"Canary Extraction in Natural Language Understanding Models","created":"2022-03-25","cited_by_count":21,"area":null},{"id":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"id":"2205.07208","title":"Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization","created":"2022-05-15","cited_by_count":19,"area":null},{"id":"2105.12995","title":"ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning","created":"2021-05-27","cited_by_count":18,"area":null},{"id":"2207.14393","title":"LAD: Language Models as Data for Zero-Shot Dialog","created":"2022-07-28","cited_by_count":18,"area":null},{"id":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"area":null},{"id":"2205.13568","title":"Learning Dialogue Representations from Consecutive Utterances","created":"2022-05-26","cited_by_count":17,"area":null},{"id":"2305.09269","title":"ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification","created":"2023-05-16","cited_by_count":17,"area":null},{"id":"2205.04006","title":"Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue System","created":"2022-05-09","cited_by_count":16,"area":null},{"id":"2207.13211","title":"A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialog","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2306.00618","title":"Effective Structured Prompting by Meta-Learning and Representative Verbalizer","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2412.15571","title":"Continual Learning Using a Kernel-Based Method Over Foundation Models","created":"2024-12-20","cited_by_count":14,"area":null},{"id":"2210.07733","title":"Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning","created":"2022-10-14","cited_by_count":13,"area":null},{"id":"2101.06514","title":"Linguistically-Enriched and Context-Aware Zero-shot Slot Filling","created":"2021-01-16","cited_by_count":12,"area":null},{"id":"2108.04445","title":"Lifelong Intent Detection via Multi-Strategy Rebalancing","created":"2021-08-10","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":"2503.08640","title":"Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention","created":"2025-03-11","cited_by_count":12,"area":null},{"id":"2105.00896","title":"Pseudo Siamese Network for Few-shot Intent Generation","created":"2021-05-03","cited_by_count":11,"area":null},{"id":"2210.00572","title":"Risk-graded Safety for Handling Medical Queries in Conversational AI","created":"2022-10-02","cited_by_count":11,"area":null},{"id":"2411.10023","title":"Model Inversion Attacks: A Survey of Approaches and Countermeasures","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2304.12982","title":"Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11","created":"2023-04-25","cited_by_count":10,"area":null},{"id":"2506.17121","title":"Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?","created":"2025-06-20","cited_by_count":10,"area":null},{"id":"2204.04637","title":"UniDU: Towards A Unified Generative Dialogue Understanding Framework","created":"2022-04-10","cited_by_count":9,"area":null},{"id":"2210.07783","title":"Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue","created":"2022-10-14","cited_by_count":9,"area":null},{"id":"2210.08909","title":"Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery","created":"2022-10-17","cited_by_count":9,"area":null},{"id":"2406.07001","title":"Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2503.23306","title":"Focus Directions Make Your Language Models Pay More Attention to Relevant Contexts","created":"2025-03-30","cited_by_count":9,"area":null},{"id":"2203.15917","title":"Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization","created":"2022-03-29","cited_by_count":8,"area":null},{"id":"2204.13021","title":"NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-04-27","cited_by_count":8,"area":null},{"id":"2412.03966","title":"Demonstration Selection for In-Context Learning via Reinforcement Learning","created":"2024-12-05","cited_by_count":8,"area":"lr"},{"id":"2601.08435","title":"Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management","created":"2026-01-13","cited_by_count":8,"area":"agents"},{"id":"2309.06917","title":"Continual Learning with Dirichlet Generative-based Rehearsal","created":"2023-09-13","cited_by_count":7,"area":"distill"},{"id":"2310.06362","title":"InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective","created":"2023-10-10","cited_by_count":7,"area":null},{"id":"2412.15563","title":"In-context Continual Learning Assisted by an External Continual Learner","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2101.12073","title":"A Neural Few-Shot Text Classification Reality Check","created":"2021-01-28","cited_by_count":6,"area":null},{"id":"2204.05158","title":"Gaining Insights into Unrecognized User Utterances in Task-Oriented Dialog Systems","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2204.05483","title":"Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Dataset","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2209.12617","title":"Evaluation of Question Answering Systems: Complexity of judging a natural language","created":"2022-09-10","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":"2305.14827","title":"Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2306.05278","title":"Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training","created":"2023-06-08","cited_by_count":5,"area":null},{"id":"2402.03038","title":"Automatic Combination of Sample Selection Strategies for Few-Shot Learning","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2403.17552","title":"Naive Bayes-based Context Extension for Large Language Models","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2403.18973","title":"Conformal Intent Classification and Clarification for Fast and Accurate Intent Recognition","created":"2024-03-27","cited_by_count":5,"area":null},{"id":"2406.13103","title":"A Generic Method for Fine-grained Category Discovery in Natural Language Texts","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2507.13949","title":"Exploiting Primacy Effect To Improve Large Language Models","created":"2025-07-18","cited_by_count":5,"area":null},{"id":"2509.22542","title":"Category Discovery: An Open-World Perspective","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2602.03128","title":"Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance","created":"2026-02-03","cited_by_count":5,"area":"agents"},{"id":"2205.11966","title":"Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy","created":"2022-05-24","cited_by_count":4,"area":null},{"id":"2301.06544","title":"Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants","created":"2023-01-16","cited_by_count":4,"area":null},{"id":"2303.16764","title":"Boosting Few-Shot Text Classification via Distribution Estimation","created":"2023-03-26","cited_by_count":4,"area":null},{"id":"2304.13292","title":"Zero-Shot Slot and Intent Detection in Low-Resource Languages","created":"2023-04-26","cited_by_count":4,"area":null},{"id":"2310.10151","title":"DNA: Denoised Neighborhood Aggregation for Fine-grained Category Discovery","created":"2023-10-16","cited_by_count":4,"area":null},{"id":"2403.18277","title":"BlendX: Complex Multi-Intent Detection with Blended Patterns","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2404.14415","title":"Domain Adaptation in Intent Classification Systems: A Review","created":"2024-03-26","cited_by_count":4,"area":null},{"id":"2512.17452","title":"KV Admission: Learning What to Write for Efficient Long-Context LLM Inference","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2110.15717","title":"LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2205.12662","title":"DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2209.09146","title":"Semantic-based Pre-training for Dialogue Understanding","created":"2022-09-19","cited_by_count":3,"area":null},{"id":"2309.11065","title":"UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2310.18619","title":"Dense Retrieval as Indirect Supervision for Large-space Decision Making","created":"2023-10-28","cited_by_count":3,"area":null},{"id":"2311.17376","title":"CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs","created":"2023-11-29","cited_by_count":3,"area":null}],"next_cursor":"100"}