{"list":"other","total":63,"rows":[{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"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":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"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":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"2304.08177","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","created":"2023-04-17","cited_by_count":305},{"id":"2209.10063","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","created":"2022-09-21","cited_by_count":298},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"id":"2305.12474","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","created":"2023-05-21","cited_by_count":186},{"id":"2302.07736","title":"Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech","created":"2023-02-11","cited_by_count":166},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151},{"id":"2309.11325","title":"DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services","created":"2023-09-20","cited_by_count":120},{"id":"1911.12011","title":"JEC-QA: A Legal-Domain Question Answering Dataset","created":"2019-11-27","cited_by_count":116},{"id":"2105.03887","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","created":"2021-05-09","cited_by_count":116},{"id":"2308.08833","title":"CMB: A Comprehensive Medical Benchmark in Chinese","created":"2023-08-17","cited_by_count":115},{"id":"2305.17306","title":"Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance","created":"2023-05-26","cited_by_count":102},{"id":"2211.05655","title":"DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering","created":"2022-11-10","cited_by_count":96},{"id":"2303.14742","title":"Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases","created":"2023-03-26","cited_by_count":86},{"id":"2306.09296","title":"KoLA: Carefully Benchmarking World Knowledge of Large Language Models","created":"2023-06-15","cited_by_count":85},{"id":"2212.14402","title":"GPT Takes the Bar Exam","created":"2022-12-29","cited_by_count":65},{"id":"2307.13692","title":"ARB: Advanced Reasoning Benchmark for Large Language Models","created":"2023-07-25","cited_by_count":60},{"id":"2305.15062","title":"Lawyer LLaMA Technical Report","created":"2023-05-24","cited_by_count":54},{"id":"2308.09975","title":"FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models","created":"2023-08-19","cited_by_count":52},{"id":"2204.04859","title":"A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges","created":"2022-04-11","cited_by_count":50},{"id":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40},{"id":"2203.08556","title":"LEVEN: A Large-Scale Chinese Legal Event Detection Dataset","created":"2022-03-16","cited_by_count":36},{"id":"2204.10994","title":"MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction","created":"2022-04-23","cited_by_count":33},{"id":"2304.12202","title":"ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark","created":"2023-03-09","cited_by_count":33},{"id":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33},{"id":"2305.09612","title":"Large Language Models are Built-in Autoregressive Search Engines","created":"2023-05-16","cited_by_count":27},{"id":"2209.10372","title":"WeLM: A Well-Read Pre-trained Language Model for Chinese","created":"2022-09-21","cited_by_count":19},{"id":"2104.10726","title":"Learning Fine-grained Fact-Article Correspondence in Legal Cases","created":"2021-04-21","cited_by_count":15},{"id":"2309.01940","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models","created":"2023-09-05","cited_by_count":15},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14},{"id":"2112.06370","title":"Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer","created":"2021-12-13","cited_by_count":13},{"id":"2208.13078","title":"MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages","created":"2022-08-27","cited_by_count":13},{"id":"2305.09249","title":"xPQA: Cross-Lingual Product Question Answering across 12 Languages","created":"2023-05-16","cited_by_count":10},{"id":"2301.12847","title":"Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks","created":"2023-01-30","cited_by_count":9},{"id":"2308.06032","title":"Large Language Models in Cryptocurrency Securities Cases: Can a GPT Model Meaningfully Assist Lawyers?","created":"2023-08-11","cited_by_count":4}],"next_cursor":null}