{"list":"other","total":53,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"2007.01852","title":"Language-agnostic BERT Sentence Embedding","created":"2020-07-03","cited_by_count":627},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"2302.14520","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","created":"2023-02-28","cited_by_count":420},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"2104.14478","title":"Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation","created":"2021-04-29","cited_by_count":338},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"2301.13867","title":"Mathematical Capabilities of ChatGPT","created":"2023-01-31","cited_by_count":268},{"id":"2310.10482","title":"xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection","created":"2023-10-16","cited_by_count":265},{"id":"2304.03439","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","created":"2023-04-07","cited_by_count":202},{"id":"2008.12009","title":"A Survey of Evaluation Metrics Used for NLG Systems","created":"2020-08-27","cited_by_count":164},{"id":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142},{"id":"2004.14564","title":"Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing","created":"2020-04-30","cited_by_count":115},{"id":"2308.07286","title":"The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation","created":"2023-08-14","cited_by_count":95},{"id":"2309.11925","title":"Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task","created":"2023-09-21","cited_by_count":88},{"id":"2303.13809","title":"Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models","created":"2023-03-24","cited_by_count":87},{"id":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79},{"id":"1808.08866","title":"A Study of Reinforcement Learning for Neural Machine Translation","created":"2018-08-27","cited_by_count":74},{"id":"2104.00054","title":"A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods","created":"2021-03-31","cited_by_count":72},{"id":"2010.13002","title":"Pre-trained Summarization Distillation","created":"2020-10-24","cited_by_count":71},{"id":"2005.03724","title":"SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization","created":"2020-05-07","cited_by_count":69},{"id":"2110.05802","title":"Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform","created":"2021-10-12","cited_by_count":66},{"id":"2302.13795","title":"ChatGPT: A Meta-Analysis after 2.5 Months","created":"2023-02-20","cited_by_count":51},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49},{"id":"2110.04392","title":"The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results","created":"2021-10-08","cited_by_count":27},{"id":"2110.04399","title":"Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors","created":"2021-10-08","cited_by_count":25},{"id":"2303.07610","title":"Exploring ChatGPT's Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences","created":"2023-03-14","cited_by_count":25},{"id":"2305.14282","title":"INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback","created":"2023-05-23","cited_by_count":22},{"id":"2110.08559","title":"FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generation","created":"2021-10-16","cited_by_count":19},{"id":"2305.11806","title":"The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics","created":"2023-05-19","cited_by_count":15},{"id":"2306.13041","title":"Towards Explainable Evaluation Metrics for Machine Translation","created":"2023-06-22","cited_by_count":15},{"id":"2209.02317","title":"Layer or Representation Space: What makes BERT-based Evaluation Metrics Robust?","created":"2022-09-06","cited_by_count":10},{"id":"2306.07486","title":"Knowledge-Prompted Estimator: A Novel Approach to Explainable Machine Translation Assessment","created":"2023-06-13","cited_by_count":3}],"next_cursor":null}