{"total":377,"rows":[{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666,"area":null},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"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":"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":"2410.24024","title":"AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents","created":"2024-10-31","cited_by_count":107,"area":"agents"},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"area":null},{"id":"2111.02735","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","created":"2021-11-04","cited_by_count":82,"area":null},{"id":"2111.10367","title":"SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech","created":"2021-11-19","cited_by_count":72,"area":null},{"id":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71,"area":null},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2106.02787","title":"BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling","created":"2021-06-05","cited_by_count":56,"area":null},{"id":"2102.01335","title":"Neural Data Augmentation via Example Extrapolation","created":"2021-02-02","cited_by_count":54,"area":null},{"id":"2103.03095","title":"A Survey on Spoken Language Understanding: Recent Advances and New Frontiers","created":"2021-03-04","cited_by_count":53,"area":null},{"id":"2111.14706","title":"ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet","created":"2021-11-29","cited_by_count":53,"area":null},{"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":"2311.05640","title":"FinGPT: Large Generative Models for a Small Language","created":"2023-11-03","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":"2205.10475","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","created":"2022-05-21","cited_by_count":45,"area":null},{"id":"2104.05845","title":"Visual Goal-Step Inference using wikiHow","created":"2021-04-12","cited_by_count":43,"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":"2203.03550","title":"When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing","created":"2022-02-17","cited_by_count":40,"area":null},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40,"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":"2402.15491","title":"API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs","created":"2024-02-23","cited_by_count":39,"area":"agents"},{"id":"2104.07081","title":"TWEAC: Transformer with Extendable QA Agent Classifiers","created":"2021-04-14","cited_by_count":37,"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":"2104.05763","title":"Few-shot Intent Classification and Slot Filling with Retrieved Examples","created":"2021-04-12","cited_by_count":35,"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":"2105.13448","title":"Open-world Machine Learning: Applications, Challenges, and Opportunities","created":"2021-05-27","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":"2602.21320","title":"Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data","created":"2026-02-24","cited_by_count":34,"area":"agents"},{"id":"2106.01925","title":"GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling","created":"2021-06-03","cited_by_count":33,"area":null},{"id":"2304.14334","title":"ZeroShotDataAug: Generating and Augmenting Training Data with ChatGPT","created":"2023-04-27","cited_by_count":32,"area":null},{"id":"2102.01502","title":"ADePT: Auto-encoder based Differentially Private Text Transformation","created":"2021-01-29","cited_by_count":31,"area":null},{"id":"2304.04256","title":"A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding","created":"2023-04-09","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":"2406.16442","title":"EmoLLM: Multimodal Emotional Understanding Meets Large Language Models","created":"2024-06-24","cited_by_count":31,"area":"mllm"},{"id":"2404.16233","title":"AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models","created":"2024-04-24","cited_by_count":30,"area":null},{"id":"2409.11968","title":"Efficacy of Synthetic Data as a Benchmark","created":"2024-09-18","cited_by_count":30,"area":"synth"},{"id":"2209.09900","title":"LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging","created":"2022-09-20","cited_by_count":29,"area":null},{"id":"2208.10400","title":"DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting","created":"2022-08-22","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":"2302.07636","title":"DP-BART for Privatized Text Rewriting under Local Differential Privacy","created":"2023-02-15","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":"2109.13023","title":"An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling","created":"2021-09-27","cited_by_count":26,"area":null},{"id":"2402.15833","title":"Prompt Perturbation Consistency Learning for Robust Language Models","created":"2024-02-24","cited_by_count":26,"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":"2103.07792","title":"Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling","created":"2021-03-13","cited_by_count":25,"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":"2105.00573","title":"Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks","created":"2021-05-02","cited_by_count":24,"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":"2310.06504","title":"Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task","created":"2023-10-10","cited_by_count":23,"area":null},{"id":"2104.07253","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2106.14464","title":"Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU","created":"2021-06-28","cited_by_count":22,"area":null},{"id":"2207.10643","title":"STOP: A dataset for Spoken Task Oriented Semantic Parsing","created":"2022-06-29","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":"2102.02925","title":"Generalized Zero-shot Intent Detection via Commonsense Knowledge","created":"2021-02-04","cited_by_count":21,"area":null},{"id":"2106.15167","title":"Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition","created":"2021-06-29","cited_by_count":21,"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":"2306.03208","title":"NLU on Data Diets: Dynamic Data Subset Selection for NLP Classification Tasks","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2408.03900","title":"Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond","created":"2024-08-07","cited_by_count":20,"area":null},{"id":"2502.08820","title":"Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model","created":"2025-02-12","cited_by_count":20,"area":"agents"},{"id":"2101.00123","title":"Intent Classification and Slot Filling for Privacy Policies","created":"2021-01-01","cited_by_count":19,"area":null},{"id":"2104.02021","title":"Intent Detection and Slot Filling for Vietnamese","created":"2021-04-05","cited_by_count":19,"area":null},{"id":"2211.04054","title":"ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications","created":"2022-11-08","cited_by_count":19,"area":null},{"id":"2211.04684","title":"Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind","created":"2022-11-09","cited_by_count":19,"area":null},{"id":"2104.07275","title":"Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing","created":"2021-04-15","cited_by_count":18,"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":"2211.05869","title":"A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding","created":"2022-11-10","cited_by_count":18,"area":null},{"id":"2305.11916","title":"F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks","created":"2023-05-21","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":"2402.12819","title":"Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance","created":"2024-02-20","cited_by_count":18,"area":null},{"id":"2104.04923","title":"Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog","created":"2021-04-11","cited_by_count":17,"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":"2106.09009","title":"End-to-End Spoken Language Understanding for Generalized Voice Assistants","created":"2021-06-16","cited_by_count":17,"area":null},{"id":"2109.07364","title":"Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU","created":"2021-09-15","cited_by_count":17,"area":null},{"id":"2204.11117","title":"Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning","created":"2022-04-23","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":"2208.05379","title":"Multi-task Active Learning for Pre-trained Transformer-based Models","created":"2022-08-10","cited_by_count":16,"area":null},{"id":"2303.08954","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","created":"2023-03-15","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":"2203.08378","title":"Transforming Sequence Tagging Into A Seq2Seq Task","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2202.11485","title":"Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences","created":"2022-02-17","cited_by_count":14,"area":null},{"id":"2203.11396","title":"Towards Textual Out-of-Domain Detection without In-Domain Labels","created":"2022-03-22","cited_by_count":14,"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":"2210.10375","title":"Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs","created":"2022-10-19","cited_by_count":14,"area":null},{"id":"2305.20080","title":"Findings of the VarDial Evaluation Campaign 2023","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2103.08886","title":"Automatic Intent-Slot Induction for Dialogue Systems","created":"2021-03-16","cited_by_count":13,"area":null},{"id":"2110.03572","title":"Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling","created":"2021-10-07","cited_by_count":13,"area":null},{"id":"2202.13840","title":"Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks","created":"2022-02-28","cited_by_count":13,"area":null},{"id":"2204.14081","title":"Few-shot learning for medical text: A systematic review","created":"2022-04-21","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}],"next_cursor":"100"}