{"list":"other","total":66,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"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":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"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":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2403.14403","title":"Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity","created":"2024-03-21","cited_by_count":451},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"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":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302},{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244},{"id":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238},{"id":"2306.05443","title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","created":"2023-06-08","cited_by_count":222},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203},{"id":"2401.15884","title":"Corrective Retrieval Augmented Generation","created":"2024-01-29","cited_by_count":197},{"id":"2305.12474","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","created":"2023-05-21","cited_by_count":186},{"id":"2502.08235","title":"The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks","created":"2025-02-12","cited_by_count":152},{"id":"2402.12659","title":"FinBen: A Holistic Financial Benchmark for Large Language Models","created":"2024-02-20","cited_by_count":141},{"id":"2211.00083","title":"WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain","created":"2022-10-31","cited_by_count":117},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117},{"id":"2308.08833","title":"CMB: A Comprehensive Medical Benchmark in Chinese","created":"2023-08-17","cited_by_count":115},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110},{"id":"2304.06588","title":"ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning","created":"2023-04-13","cited_by_count":100},{"id":"2305.12002","title":"XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters","created":"2023-05-19","cited_by_count":92},{"id":"1810.05995","title":"BLEU is Not Suitable for the Evaluation of Text Simplification","created":"2018-10-14","cited_by_count":78},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73},{"id":"2310.05002","title":"Self-Knowledge Guided Retrieval Augmentation for Large Language Models","created":"2023-10-08","cited_by_count":69},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66},{"id":"2302.09432","title":"BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark","created":"2023-02-18","cited_by_count":60},{"id":"2401.02524","title":"Comprehensive Exploration of Synthetic Data Generation: A Survey","created":"2024-01-04","cited_by_count":60},{"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":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44},{"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},{"id":"2212.08635","title":"Self-Prompting Large Language Models for Zero-Shot Open-Domain QA","created":"2022-12-16","cited_by_count":39},{"id":"2408.08808","title":"Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge","created":"2024-08-16","cited_by_count":30},{"id":"2401.12086","title":"West-of-N: Synthetic Preferences for Self-Improving Reward Models","created":"2024-01-22","cited_by_count":28},{"id":"2408.08072","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","created":"2024-08-15","cited_by_count":27},{"id":"2404.06644","title":"Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?","created":"2024-04-09","cited_by_count":22},{"id":"2410.05193","title":"RevisEval: Improving LLM-as-a-Judge via Response-Adapted References","created":"2024-10-07","cited_by_count":20},{"id":"2410.01553","title":"MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills","created":"2024-10-02","cited_by_count":17},{"id":"2410.12722","title":"WorldMedQA-V: a multilingual, multimodal medical examination dataset for multimodal language models evaluation","created":"2024-10-16","cited_by_count":11},{"id":"2202.05957","title":"Confident AI","created":"2022-02-12","cited_by_count":6}],"next_cursor":null}