{"list":"other","total":69,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"2302.09210","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","created":"2023-02-18","cited_by_count":348},{"id":"2310.10482","title":"xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection","created":"2023-10-16","cited_by_count":265},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255},{"id":"2301.07069","title":"Prompting Large Language Model for Machine Translation: A Case Study","created":"2023-01-17","cited_by_count":250},{"id":"1911.04944","title":"CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB","created":"2019-11-10","cited_by_count":177},{"id":"2212.02437","title":"In-context Examples Selection for Machine Translation","created":"2022-12-05","cited_by_count":172},{"id":"2304.04675","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","created":"2023-04-10","cited_by_count":160},{"id":"2211.09102","title":"Prompting PaLM for Translation: Assessing Strategies and Performance","created":"2022-11-16","cited_by_count":145},{"id":"2201.06642","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","created":"2022-01-17","cited_by_count":143},{"id":"2303.13780","title":"Towards Making the Most of ChatGPT for Machine Translation","created":"2023-03-24","cited_by_count":138},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116},{"id":"2004.06063","title":"BLEU might be Guilty but References are not Innocent","created":"2020-04-13","cited_by_count":110},{"id":"2308.11466","title":"SONAR: Sentence-Level Multimodal and Language-Agnostic Representations","created":"2023-08-22","cited_by_count":108},{"id":"2310.01714","title":"Large Language Models as Analogical Reasoners","created":"2023-10-03","cited_by_count":107},{"id":"2212.04092","title":"Successive Prompting for Decomposing Complex Questions","created":"2022-12-08","cited_by_count":94},{"id":"2309.11674","title":"A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models","created":"2023-09-20","cited_by_count":89},{"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":"2407.03618","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","created":"2024-07-04","cited_by_count":88},{"id":"2309.16575","title":"A Benchmark for Learning to Translate a New Language from One Grammar Book","created":"2023-09-28","cited_by_count":75},{"id":"2302.07856","title":"Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation","created":"2023-02-15","cited_by_count":74},{"id":"2007.01788","title":"TICO-19: the Translation Initiative for Covid-19","created":"2020-07-03","cited_by_count":68},{"id":"2403.16512","title":"LLMs Are Few-Shot In-Context Low-Resource Language Learners","created":"2024-03-25","cited_by_count":68},{"id":"2303.01911","title":"Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM","created":"2023-03-03","cited_by_count":59},{"id":"2301.13294","title":"Adaptive Machine Translation with Large Language Models","created":"2023-01-30","cited_by_count":58},{"id":"2404.13813","title":"From LLM to NMT: Advancing Low-Resource Machine Translation with Claude","created":"2024-04-22","cited_by_count":58},{"id":"2010.15535","title":"Unbabel's Participation in the WMT20 Metrics Shared Task","created":"2020-10-29","cited_by_count":56},{"id":"2406.01771","title":"LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback","created":"2024-06-03","cited_by_count":51},{"id":"2305.04118","title":"Exploring Human-Like Translation Strategy with Large Language Models","created":"2023-05-06","cited_by_count":44},{"id":"2311.09336","title":"LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback","created":"2023-11-15","cited_by_count":39},{"id":"2402.16379","title":"TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement","created":"2024-02-26","cited_by_count":39},{"id":"2410.03115","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","created":"2024-10-04","cited_by_count":36},{"id":"2409.06790","title":"Translating Step-by-Step: Decomposing the Translation Process for Improved Translation Quality of Long-Form Texts","created":"2024-09-10","cited_by_count":31},{"id":"2306.03856","title":"Iterative Translation Refinement with Large Language Models","created":"2023-06-06","cited_by_count":27},{"id":"2404.07851","title":"Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations","created":"2024-04-11","cited_by_count":22},{"id":"2408.00397","title":"In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation","created":"2024-08-01","cited_by_count":22},{"id":"2305.17367","title":"Augmenting Large Language Model Translators via Translation Memories","created":"2023-05-27","cited_by_count":21},{"id":"2212.08486","title":"BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric","created":"2022-12-16","cited_by_count":16},{"id":"2305.06575","title":"Chain-of-Dictionary Prompting Elicits Translation in Large Language Models","created":"2023-05-11","cited_by_count":16},{"id":"2406.08707","title":"mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus","created":"2024-06-13","cited_by_count":9},{"id":"1909.12131","title":"MinWikiSplit: A Sentence Splitting Corpus with Minimal Propositions","created":"2019-09-26","cited_by_count":8},{"id":"2404.02835","title":"Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison","created":"2024-04-03","cited_by_count":7},{"id":"2410.06634","title":"Tree of Problems: Improving structured problem solving with compositionality","created":"2024-10-09","cited_by_count":3},{"id":"2310.15612","title":"Machine Translation for Nko: Tools, Corpora and Baseline Results","created":"2023-10-24","cited_by_count":2}],"next_cursor":null}