{"list":"other","total":62,"rows":[{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423},{"id":"2304.08177","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","created":"2023-04-17","cited_by_count":305},{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232},{"id":"2005.00456","title":"USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation","created":"2020-05-01","cited_by_count":188},{"id":"1908.06083","title":"Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack","created":"2019-08-17","cited_by_count":176},{"id":"2307.00184","title":"Personality Traits in Large Language Models","created":"2023-07-01","cited_by_count":169},{"id":"1711.01731","title":"A Survey on Dialogue Systems: Recent Advances and New Frontiers","created":"2017-11-06","cited_by_count":162},{"id":"2303.04360","title":"Does Synthetic Data Generation of LLMs Help Clinical Text Mining?","created":"2023-03-08","cited_by_count":154},{"id":"1905.05709","title":"Challenges in Building Intelligent Open-domain Dialog Systems","created":"2019-05-13","cited_by_count":147},{"id":"1811.00671","title":"Dialogue Natural Language Inference","created":"2018-11-01","cited_by_count":135},{"id":"2304.04339","title":"Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study","created":"2023-04-10","cited_by_count":96},{"id":"2009.13570","title":"DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue","created":"2020-09-28","cited_by_count":89},{"id":"2303.01248","title":"Can ChatGPT Assess Human Personalities? A General Evaluation Framework","created":"2023-03-01","cited_by_count":70},{"id":"2305.15038","title":"Is GPT-4 a Good Data Analyst?","created":"2023-05-24","cited_by_count":70},{"id":"1801.03604","title":"Conversational AI: The Science Behind the Alexa Prize","created":"2018-01-11","cited_by_count":63},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63},{"id":"2305.11792","title":"Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs","created":"2023-05-19","cited_by_count":62},{"id":"2304.09582","title":"Is ChatGPT Equipped with Emotional Dialogue Capabilities?","created":"2023-04-19","cited_by_count":54},{"id":"2305.13455","title":"Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents","created":"2023-05-22","cited_by_count":54},{"id":"2011.00564","title":"Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey","created":"2020-11-01","cited_by_count":51},{"id":"2107.03175","title":"A Survey on Dialogue Summarization: Recent Advances and New Frontiers","created":"2021-07-07","cited_by_count":51},{"id":"2305.14288","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","created":"2023-05-23","cited_by_count":51},{"id":"2307.15020","title":"SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark","created":"2023-07-27","cited_by_count":50},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39},{"id":"2306.04556","title":"StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Code","created":"2023-06-07","cited_by_count":32},{"id":"2109.06427","title":"Commonsense-Focused Dialogues for Response Generation: An Empirical Study","created":"2021-09-14","cited_by_count":30},{"id":"2110.05456","title":"Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation","created":"2021-10-11","cited_by_count":29},{"id":"2307.03952","title":"Is ChatGPT a Good Personality Recognizer? A Preliminary Study","created":"2023-07-08","cited_by_count":26},{"id":"2304.12986","title":"Measuring Massive Multitask Chinese Understanding","created":"2023-04-25","cited_by_count":25},{"id":"2012.02553","title":"DDRel: A New Dataset for Interpersonal Relation Classification in Dyadic Dialogues","created":"2020-12-04","cited_by_count":13}],"next_cursor":null}