{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"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":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"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":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361},{"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":"2005.03754","title":"FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization","created":"2020-05-07","cited_by_count":293},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201},{"id":"2005.00456","title":"USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation","created":"2020-05-01","cited_by_count":188},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155},{"id":"1711.04434","title":"Faithful to the Original: Fact Aware Neural Abstractive Summarization","created":"2017-11-13","cited_by_count":141},{"id":"2402.12659","title":"FinBen: A Holistic Financial Benchmark for Large Language Models","created":"2024-02-20","cited_by_count":141},{"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":"2010.03994","title":"GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems","created":"2020-10-08","cited_by_count":76},{"id":"2405.18137","title":"Exploiting LLM Quantization","created":"2024-05-28","cited_by_count":65},{"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":"1904.01803","title":"GFF: Gated Fully Fusion for Semantic Segmentation","created":"2019-04-03","cited_by_count":57},{"id":"1904.03371","title":"Evaluating Coherence in Dialogue Systems using Entailment","created":"2019-04-06","cited_by_count":53},{"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":"2203.07228","title":"FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing","created":"2022-03-14","cited_by_count":49},{"id":"2305.01526","title":"Huatuo-26M, a Large-scale Chinese Medical QA Dataset","created":"2023-05-02","cited_by_count":46},{"id":"2402.11550","title":"LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration","created":"2024-02-18","cited_by_count":38},{"id":"2409.20288","title":"LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models","created":"2024-09-30","cited_by_count":37},{"id":"2402.01742","title":"Towards Optimizing the Costs of LLM Usage","created":"2024-01-29","cited_by_count":33},{"id":"2112.04139","title":"Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand","created":"2021-12-08","cited_by_count":32},{"id":"2301.12017","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","created":"2023-01-27","cited_by_count":23},{"id":"2106.00507","title":"Towards Quantifiable Dialogue Coherence Evaluation","created":"2021-06-01","cited_by_count":21},{"id":"2505.10483","title":"UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation","created":"2025-05-15","cited_by_count":15},{"id":"2505.17267","title":"GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations","created":"2025-05-22","cited_by_count":15},{"id":"2411.06084","title":"Optimizing Large Language Models through Quantization: A Comparative Analysis of PTQ and QAT Techniques","created":"2024-11-09","cited_by_count":10},{"id":"2411.09497","title":"The Use of Readability Metrics in Legal Text: A Systematic Literature Review","created":"2024-11-14","cited_by_count":4},{"id":"2411.10137","title":"Legal Evalutions and Challenges of Large Language Models","created":"2024-11-15","cited_by_count":4}],"next_cursor":null}