{"total":142,"rows":[{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648,"area":null},{"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":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231,"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":"2302.05698","title":"Compositional Exemplars for In-context Learning","created":"2023-02-11","cited_by_count":144,"area":null},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"area":null},{"id":"2409.15700","title":"Making Text Embedders Few-Shot Learners","created":"2024-09-24","cited_by_count":79,"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":"2401.11624","title":"In-context Learning with Retrieved Demonstrations for Language Models: A Survey","created":"2024-01-21","cited_by_count":70,"area":null},{"id":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68,"area":null},{"id":"2305.14907","title":"Coverage-based Example Selection for In-Context Learning","created":"2023-05-24","cited_by_count":59,"area":null},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"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":"2109.08877","title":"DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation","created":"2021-09-18","cited_by_count":46,"area":null},{"id":"2203.08388","title":"MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages","created":"2022-03-16","cited_by_count":41,"area":null},{"id":"2311.09278","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","created":"2023-11-15","cited_by_count":39,"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":"2110.08458","title":"Controllable Semantic Parsing via Retrieval Augmentation","created":"2021-10-16","cited_by_count":35,"area":null},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2110.07679","title":"GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems","created":"2021-10-14","cited_by_count":31,"area":null},{"id":"2402.16671","title":"StructLM: Towards Building Generalist Models for Structured Knowledge Grounding","created":"2024-02-26","cited_by_count":29,"area":null},{"id":"2305.15678","title":"Revisiting non-English Text Simplification: A Unified Multilingual Benchmark","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2206.10139","title":"Insights into Pre-training via Simpler Synthetic Tasks","created":"2022-06-21","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":"2201.13405","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","created":"2022-01-31","cited_by_count":23,"area":null},{"id":"2212.13492","title":"MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing","created":"2022-12-27","cited_by_count":22,"area":null},{"id":"2106.02171","title":"nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?","created":"2021-06-03","cited_by_count":21,"area":null},{"id":"2210.07074","title":"CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing","created":"2022-10-13","cited_by_count":21,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","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":"2101.00123","title":"Intent Classification and Slot Filling for Privacy Policies","created":"2021-01-01","cited_by_count":19,"area":null},{"id":"2104.07554","title":"Zero-Shot Cross-lingual Semantic Parsing","created":"2021-04-15","cited_by_count":19,"area":null},{"id":"2202.04350","title":"pNLP-Mixer: an Efficient all-MLP Architecture for Language","created":"2022-02-09","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":"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":"2303.08954","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","created":"2023-03-15","cited_by_count":16,"area":null},{"id":"2410.00927","title":"Text Clustering as Classification with LLMs","created":"2024-09-30","cited_by_count":16,"area":null},{"id":"2203.08378","title":"Transforming Sequence Tagging Into A Seq2Seq Task","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2205.12585","title":"TAGPRIME: A Unified Framework for Relational Structure Extraction","created":"2022-05-25","cited_by_count":15,"area":null},{"id":"2209.14899","title":"Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsing","created":"2022-09-29","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":"2206.10668","title":"BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing","created":"2022-06-21","cited_by_count":13,"area":null},{"id":"2306.17674","title":"X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents","created":"2023-06-30","cited_by_count":13,"area":null},{"id":"2406.14739","title":"Learning to Retrieve Iteratively for In-Context Learning","created":"2024-06-20","cited_by_count":13,"area":null},{"id":"2305.13917","title":"Generating Data for Symbolic Language with Large Language Models","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2603.19223","title":"F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World","created":"2026-03-19","cited_by_count":12,"area":null},{"id":"2105.02472","title":"XeroAlign: Zero-Shot Cross-lingual Transformer Alignment","created":"2021-05-06","cited_by_count":11,"area":null},{"id":"2106.02134","title":"Syntax-augmented Multilingual BERT for Cross-lingual Transfer","created":"2021-06-03","cited_by_count":11,"area":null},{"id":"2209.12577","title":"Meta-Learning a Cross-lingual Manifold for Semantic Parsing","created":"2022-09-26","cited_by_count":11,"area":null},{"id":"2302.11521","title":"How Does In-Context Learning Help Prompt Tuning?","created":"2023-02-22","cited_by_count":11,"area":null},{"id":"2104.07224","title":"Low-Resource Task-Oriented Semantic Parsing via Intrinsic Modeling","created":"2021-04-15","cited_by_count":10,"area":null},{"id":"2305.08677","title":"Natural Language Decomposition and Interpretation of Complex Utterances","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2205.11152","title":"Cross-lingual Lifelong Learning","created":"2022-05-23","cited_by_count":9,"area":null},{"id":"2209.06767","title":"Parameter-Efficient Finetuning for Robust Continual Multilingual Learning","created":"2022-09-14","cited_by_count":9,"area":null},{"id":"2309.08929","title":"Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding","created":"2023-09-16","cited_by_count":9,"area":null},{"id":"2402.06733","title":"NICE: To Optimize In-Context Examples or Not?","created":"2024-02-09","cited_by_count":9,"area":null},{"id":"2406.11890","title":"Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2210.12540","title":"EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching","created":"2022-10-22","cited_by_count":8,"area":null},{"id":"2411.10670","title":"IntentGPT: Few-shot Intent Discovery with Large Language Models","created":"2024-11-16","cited_by_count":8,"area":null},{"id":"2508.17744","title":"Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks","created":"2025-08-25","cited_by_count":8,"area":null},{"id":"2510.02294","title":"F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data","created":"2025-10-02","cited_by_count":8,"area":null},{"id":"2202.00901","title":"Retrieve-and-Fill for Scenario-based Task-Oriented Semantic Parsing","created":"2022-02-02","cited_by_count":7,"area":null},{"id":"2203.09982","title":"CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding","created":"2022-03-18","cited_by_count":7,"area":null},{"id":"2403.00462","title":"LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues","created":"2024-03-01","cited_by_count":7,"area":null},{"id":"2204.04735","title":"Reducing Model Jitter: Stable Re-training of Semantic Parsers in Production Environments","created":"2022-04-10","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":"2212.10815","title":"ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Models","created":"2022-12-21","cited_by_count":6,"area":null},{"id":"2311.09606","title":"GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2405.20468","title":"MTEB-French: Resources for French Sentence Embedding Evaluation and Analysis","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2407.01411","title":"HyperLoader: Integrating Hypernetwork-Based LoRA and Adapter Layers into Multi-Task Transformers for Sequence Labelling","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2501.09749","title":"Enhancing Lexicon-Based Text Embeddings with Large Language Models","created":"2025-01-16","cited_by_count":6,"area":null},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2105.13496","title":"Diagnosing Transformers in Task-Oriented Semantic Parsing","created":"2021-05-27","cited_by_count":5,"area":null},{"id":"2306.04085","title":"XSemPLR: Cross-Lingual Semantic Parsing in Multiple Natural Languages and Meaning Representations","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2505.13136","title":"New Encoders for German Trained from Scratch: Comparing ModernGBERT with Converted LLM2Vec Models","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2505.19800","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2106.03777","title":"X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2109.01583","title":"Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding","created":"2021-09-03","cited_by_count":4,"area":null},{"id":"2302.09424","title":"Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation","created":"2023-02-18","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":"2310.13583","title":"Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2401.13621","title":"DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2402.02078","title":"Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties","created":"2024-02-03","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":"2509.12892","title":"Conan-Embedding-v2: Training an LLM from Scratch for Text Embeddings","created":"2025-09-16","cited_by_count":4,"area":null},{"id":"2205.03656","title":"Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding","created":"2022-05-07","cited_by_count":3,"area":null},{"id":"2301.12920","title":"Active Learning for Multilingual Semantic Parser","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2302.05454","title":"Distillation of encoder-decoder transformers for sequence labelling","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2305.12737","title":"The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning","created":"2023-05-22","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":"2506.04579","title":"Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2506.07438","title":"LGAI-EMBEDDING-Preview Technical Report","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2511.15424","title":"LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2605.23033","title":"Uncovering the Latent Potential of Deep Intermediate Representations","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2109.14350","title":"Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU Models","created":"2021-09-29","cited_by_count":2,"area":null}],"next_cursor":"100"}