{"total":433,"rows":[{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640,"area":null},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472,"area":null},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"area":"moe"},{"id":"2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","created":"2026-03-30","cited_by_count":309,"area":null},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286,"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":"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":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"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":"2109.14739","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","created":"2021-09-29","cited_by_count":139,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"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":"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":"2402.17834","title":"Stable LM 2 1.6B Technical Report","created":"2024-02-27","cited_by_count":90,"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":"2402.02315","title":"A Survey of Large Language Models in Finance (FinLLMs)","created":"2024-02-04","cited_by_count":79,"area":null},{"id":"2409.15700","title":"Making Text Embedders Few-Shot Learners","created":"2024-09-24","cited_by_count":79,"area":null},{"id":"2307.00524","title":"Large Language Models Enable Few-Shot Clustering","created":"2023-07-02","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":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2101.00403","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words","created":"2021-01-02","cited_by_count":63,"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":"2109.14076","title":"RAFT: A Real-World Few-Shot Text Classification Benchmark","created":"2021-09-28","cited_by_count":44,"area":null},{"id":"2106.08616","title":"Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training","created":"2021-06-16","cited_by_count":42,"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":"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":"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":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","cited_by_count":36,"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":"2211.15115","title":"Generalized Category Discovery with Decoupled Prototypical Network","created":"2022-11-28","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":"2109.07460","title":"Efficient Domain Adaptation of Language Models via Adaptive Tokenization","created":"2021-09-15","cited_by_count":34,"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":"2310.09130","title":"Split-and-Denoise: Protect large language model inference with local differential privacy","created":"2023-10-13","cited_by_count":32,"area":null},{"id":"2305.03236","title":"A Survey on Out-of-Distribution Detection in NLP","created":"2023-05-05","cited_by_count":31,"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":"2104.11882","title":"Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System","created":"2021-04-24","cited_by_count":30,"area":null},{"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":"2403.02990","title":"Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges","created":"2024-03-05","cited_by_count":30,"area":null},{"id":"2406.15981","title":"Serial Position Effects of Large Language Models","created":"2024-06-23","cited_by_count":30,"area":null},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2205.12914","title":"New Intent Discovery with Pre-training and Contrastive Learning","created":"2022-05-25","cited_by_count":28,"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":"2109.05782","title":"Effectiveness of Pre-training for Few-shot Intent Classification","created":"2021-09-13","cited_by_count":27,"area":null},{"id":"2310.13206","title":"Primacy Effect of ChatGPT","created":"2023-10-20","cited_by_count":27,"area":null},{"id":"2402.09642","title":"Answer is All You Need: Instruction-following Text Embedding via Answering the Question","created":"2024-02-15","cited_by_count":27,"area":null},{"id":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","cited_by_count":26,"area":null},{"id":"2406.12203","title":"InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context","created":"2024-06-18","cited_by_count":26,"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":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","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":"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":"2110.15063","title":"TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition","created":"2021-09-13","cited_by_count":24,"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":"2402.02526","title":"CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition","created":"2024-02-04","cited_by_count":23,"area":"moe"},{"id":"2405.10542","title":"Benchmarking Large Language Models on CFLUE -- A Chinese Financial Language Understanding Evaluation Dataset","created":"2024-05-17","cited_by_count":23,"area":null},{"id":"2106.04564","title":"Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection","created":"2021-06-08","cited_by_count":22,"area":null},{"id":"2305.19783","title":"IDAS: Intent Discovery with Abstractive Summarization","created":"2023-05-31","cited_by_count":22,"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":"2312.17543","title":"Building Efficient Universal Classifiers with Natural Language Inference","created":"2023-12-29","cited_by_count":22,"area":null},{"id":"2404.12526","title":"Adaptive Memory Replay for Continual Learning","created":"2024-04-18","cited_by_count":22,"area":null},{"id":"2410.22815","title":"Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients","created":"2024-10-30","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":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"id":"2502.11367","title":"Sparse Autoencoder Features for Classifications and Transferability","created":"2025-02-17","cited_by_count":21,"area":"mechinterp"},{"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":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","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":"2204.07128","title":"Label Semantic Aware Pre-training for Few-shot Text Classification","created":"2022-04-14","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":"2212.10873","title":"Prompt-Augmented Linear Probing: Scaling beyond the Limit of Few-shot In-Context Learners","created":"2022-12-21","cited_by_count":18,"area":null},{"id":"2308.10529","title":"SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding","created":"2023-08-21","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":"2310.10176","title":"Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT","created":"2023-10-16","cited_by_count":16,"area":null},{"id":"2203.05823","title":"Learning Discriminative Representations and Decision Boundaries for Open Intent Detection","created":"2022-03-11","cited_by_count":15,"area":null},{"id":"2212.10455","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-12-20","cited_by_count":15,"area":null},{"id":"2302.09852","title":"Unsupervised Layer-wise Score Aggregation for Textual OOD Detection","created":"2023-02-20","cited_by_count":15,"area":null},{"id":"2312.10897","title":"Generalized Category Discovery with Large Language Models in the Loop","created":"2023-12-18","cited_by_count":15,"area":null},{"id":"2503.05066","title":"Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts","created":"2025-03-07","cited_by_count":15,"area":"moe"},{"id":"2503.19693","title":"AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation","created":"2025-03-25","cited_by_count":15,"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":"2306.10087","title":"ActiveGLAE: A Benchmark for Deep Active Learning with Transformers","created":"2023-06-16","cited_by_count":14,"area":null},{"id":"2402.17256","title":"Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection","created":"2024-02-27","cited_by_count":14,"area":null},{"id":"2404.09296","title":"Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT","created":"2024-04-14","cited_by_count":14,"area":null},{"id":"2410.15035","title":"Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging","created":"2024-10-19","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":"2312.07887","title":"Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models","created":"2023-12-13","cited_by_count":13,"area":null},{"id":"2409.07132","title":"LLM-based feature generation from text for interpretable machine learning","created":"2024-09-11","cited_by_count":13,"area":null},{"id":"2410.05258","title":"Differential Transformer","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2505.16225","title":"MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning","created":"2025-05-22","cited_by_count":13,"area":null}],"next_cursor":"100"}