--- title: "Microsoft — works of 2022: 19 papers, the most cited first" description: "19 works of Microsoft from 2022 in our library, the most cited first. Among them: What Makes Good In-Context Examples for GPT-3?…" canonical: "https://research.elamur.ai/free/en/companies/microsoft/year/2022/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/companies/microsoft/year/2022/) [home](https://md.research.elamur.ai/free/en/) / [institutions](https://md.research.elamur.ai/free/en/orgs/) / [companies](https://md.research.elamur.ai/free/en/companies/) / [Microsoft](https://md.research.elamur.ai/free/en/companies/microsoft/) / 2022 # Works of Microsoft from 2022 19 works · the most cited first · [← Microsoft](https://md.research.elamur.ai/free/en/companies/microsoft/) 1. [**What Makes Good In-Context Examples for GPT-3? Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures**Jiachang Liu, Dinghan Shen, Yizhe Zhang, et al.*2022 · 1,238 citations*](https://md.research.elamur.ai/free/en/papers/liu-2022-what-makes-good-context-examples/) 2. [**Editing Models with Task Arithmetic arXiv:2212.04089**Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, et al.*2022 · 376 citations*](https://md.research.elamur.ai/free/en/papers/ilharco-2022-editing-models-task-arithmetic/) 3. [**Generate rather than Retrieve: Large Language Models are Strong Context Generators arXiv:2209.10063**Wenhao Yu, Dan Iter, Shuohang Wang, et al.*2022 · 280 citations*](https://md.research.elamur.ai/free/en/papers/yu-2022-generate-rather-than-retrieve-large/) 4. [**Results of WMT22 Metrics Shared Task: Stop Using BLEU – Neural Metrics Are Better and More Robust**Markus Freitag, Ricardo Rei, Nitika Mathur, et al.*2022 · 263 citations*](https://md.research.elamur.ai/free/en/papers/freitag-2022-results-wmt22-metrics-shared-task/) 5. [**Prompting GPT-3 To Be Reliable arXiv:2210.09150**Chenglei Si, Zhe Gan, Zhengyuan Yang, et al.*2022 · 207 citations*](https://md.research.elamur.ai/free/en/papers/si-2022-prompting-gpt-3-reliable/) 6. **[Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://md.research.elamur.ai/free/en/papers/zhong-2022-unified-multi-dimensional-evaluator-text/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Ming Zhong, Yang Liu, Da Yin, et al.*2022 · 205 citations* 7. **[AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages](https://md.research.elamur.ai/free/en/papers/ebrahimi-2022-americasnli-evaluating-zero-shot-natural/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, et al.*2022 · 163 citations* 8. **[Impact of Pretraining Term Frequencies on Few-Shot Numerical Reasoning](https://md.research.elamur.ai/free/en/papers/razeghi-2022-impact-pretraining-term-frequencies-few/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Yasaman Razeghi, Robert L Logan IV, Matt Gardner, et al.*2022 · 162 citations* 9. **[A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation](https://md.research.elamur.ai/free/en/papers/adelani-2022-few-thousand-translations-go-long/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**David Ifeoluwa Adelani, Jesujoba Oluwadara Alabi, Angela Fan, et al.*2022 · 155 citations* 10. **[IndicBART: A Pre-trained Model for Indic Natural Language Generation](https://md.research.elamur.ai/free/en/papers/dabre-2022-indicbart-pre-trained-model-indic/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Raj Dabre, Himani Shrotriya, Anoop Kunchukuttan, et al.*2022 · 141 citations* 11. **[A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://md.research.elamur.ai/free/en/papers/liu-2022-token-level-reference-free-hallucination/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Tianyu Liu, Yizhe Zhang, Chris Brockett, et al.*2022 · 140 citations* 12. **[AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning](https://md.research.elamur.ai/free/en/papers/wang-2022-adamix-mixture-adaptations-parameter-efficient/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, et al.*2022 · 132 citations* 13. **[Controllable Natural Language Generation with Contrastive Prefixes](https://md.research.elamur.ai/free/en/papers/qian-2022-controllable-natural-language-generation-contrastive/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jing Qian, Li Dong, Yelong Shen, et al.*2022 · 128 citations* 14. **[XLM-E: Cross-lingual Language Model Pre-training via ELECTRA](https://md.research.elamur.ai/free/en/papers/chi-2022-xlm-e-cross-lingual-language/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Zewen Chi, Shaohan Huang, Li Dong, et al.*2022 · 126 citations* 15. **[KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering](https://md.research.elamur.ai/free/en/papers/yu-2022-kg-fid-infusing-knowledge-graph/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Donghan Yu, Chenguang Zhu, Yuwei Fang, et al.*2022 · 115 citations* 16. [**NTREX-128 – News Test References for MT Evaluation of 128 Languages Proceedings of the First Workshop on Scaling Up Multilingual Evaluation**Christian Federmann, Tom Kocmi, Ying Xin*2022 · 104 citations*](https://md.research.elamur.ai/free/en/papers/federmann-2022-ntrex-128-news-test-references/) 17. **[MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset](https://md.research.elamur.ai/free/en/papers/fomicheva-2022-mlqe-pe-multilingual-quality-estimation/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Marina Fomicheva, Shuo Sun, Erick Fonseca, et al.*2022 · 76 citations* 18. **[The Persian Dependency Treebank Made Universal](https://md.research.elamur.ai/free/en/papers/safari-2022-persian-dependency-treebank-made-universal/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Pegah Safari, Mohammad Sadegh Rasooli, Amirsaeid Moloodi, et al.*2022 · 5 citations* 19. **[Examining Political Rhetoric with Epistemic Stance Detection](https://md.research.elamur.ai/free/en/papers/gupta-2022-examining-political-rhetoric-epistemic-stance/) [Workshop on Natural Language Processing and Computational Social Science (NLP+CSS)](https://md.research.elamur.ai/free/en/venues/nlpcss/)**Ankita Gupta, Su Lin Blodgett, Justin H Gross, et al.*2022 · 2 citations* - [← back to](https://md.research.elamur.ai/free/en/companies/microsoft/) — Microsoft