{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2203.05794","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","created":"2022-03-11","cited_by_count":801},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"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},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"2103.15316","title":"Whitening Sentence Representations for Better Semantics and Faster Retrieval","created":"2021-03-29","cited_by_count":202},{"id":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175},{"id":"2311.08692","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","created":"2023-11-15","cited_by_count":145},{"id":"2008.09470","title":"Top2Vec: Distributed Representations of Topics","created":"2020-08-19","cited_by_count":126},{"id":"2304.10548","title":"Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding","created":"2023-04-17","cited_by_count":82},{"id":"2004.07737","title":"Cross-lingual Contextualized Topic Models with Zero-shot Learning","created":"2020-04-16","cited_by_count":67},{"id":"2306.14924","title":"LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding","created":"2023-06-23","cited_by_count":64},{"id":"2309.13567","title":"MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models","created":"2023-09-24","cited_by_count":63},{"id":"2303.15727","title":"Evaluation of ChatGPT for NLP-based Mental Health Applications","created":"2023-03-28","cited_by_count":53},{"id":"2304.03347","title":"Towards Interpretable Mental Health Analysis with Large Language Models","created":"2023-04-06","cited_by_count":53},{"id":"2310.10467","title":"Stance Detection with Collaborative Role-Infused LLM-Based Agents","created":"2023-10-16","cited_by_count":53},{"id":"2407.12391","title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","created":"2024-07-17","cited_by_count":46},{"id":"2307.11991","title":"Psy-LLM: Scaling up Global Mental Health Psychological Services with AI-based Large Language Models","created":"2023-07-22","cited_by_count":36},{"id":"2310.17526","title":"Can large language models replace humans in the systematic review process? Evaluating GPT-4's efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages","created":"2023-10-26","cited_by_count":36},{"id":"2401.02984","title":"Large Language Models in Mental Health Care: a Scoping Review","created":"2024-01-01","cited_by_count":34},{"id":"2403.04801","title":"Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs","created":"2024-03-05","cited_by_count":33},{"id":"2307.02179","title":"Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning","created":"2023-07-05","cited_by_count":32},{"id":"2407.09519","title":"Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency","created":"2024-06-19","cited_by_count":31},{"id":"2403.02990","title":"Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges","created":"2024-03-05","cited_by_count":30},{"id":"2309.08631","title":"Large Language Models Can Infer Psychological Dispositions of Social Media Users","created":"2023-09-13","cited_by_count":29},{"id":"2404.00344","title":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","created":"2024-03-30","cited_by_count":22},{"id":"2205.11308","title":"Symptom Identification for Interpretable Detection of Multiple Mental Disorders","created":"2022-05-23","cited_by_count":20},{"id":"2307.16457","title":"A Benchmark for Understanding Dialogue Safety in Mental Health Support","created":"2023-07-31","cited_by_count":13},{"id":"2402.14568","title":"LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition","created":"2024-02-22","cited_by_count":11},{"id":"2410.13006","title":"LLM Chain Ensembles for Scalable and Accurate Data Annotation","created":"2024-10-16","cited_by_count":11},{"id":"2406.16203","title":"LLMs' Classification Performance is Overclaimed","created":"2024-06-23","cited_by_count":6},{"id":"2408.04649","title":"Chain of Stance: Stance Detection with Large Language Models","created":"2024-08-03","cited_by_count":5}],"next_cursor":null}