---
title: "Jason Phang — all works — Elamur Research"
description: "All 29 works of Jason Phang in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/jason-phang/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jason-phang/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Jason Phang](https://md.research.elamur.ai/free/en/authors/jason-phang/) / all works

# Jason Phang — all works

29 works · [← Jason Phang](https://md.research.elamur.ai/free/en/authors/jason-phang/)

1. **[BLOOM: A 176B-Parameter Open-Access Multilingual Language Model ↗](https://arxiv.org/abs/2211.05100) arXiv:2211.05100 · no summary yet**BigScience Workshop et al.*2022 · 1,606 citations*
2. **[GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://md.research.elamur.ai/free/en/papers/black-2022-gpt-neox-20b-open-source/) [BigScience Episode – Workshop on Challenges & Perspectives in Creating Large Language Models](https://md.research.elamur.ai/free/en/venues/bigscience/)**Sidney Black, Stella Biderman, Eric Hallahan, et al.*2022 · 831 citations*
3. **[Deep Neural Networks Improve Radiologists’ Performance in Breast Cancer Screening ↗](https://doi.org/10.1109/tmi.2019.2945514) IEEE Transactions on Medical Imaging · no summary yet**Nan Wu et al.*2019 · 703 citations*
4. [**Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks arXiv:1811.01088**Jason Phang, Thibault Févry, Samuel R. Bowman*2018 · 503 citations*](https://md.research.elamur.ai/free/en/papers/phang-2018-sentence-encoders-stilts-supplementary-training/)
5. **[BBQ: A hand-built bias benchmark for question answering](https://md.research.elamur.ai/free/en/papers/parrish-2022-bbq-hand-built-bias-benchmark/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Alicia Parrish, Angelica Chen, Nikita Nangia, et al.*2022 · 497 citations*
6. **[Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?](https://md.research.elamur.ai/free/en/papers/pruksachatkun-2020-intermediate-task-transfer-learning-pretrained/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Yada Pruksachatkun, Jason Phang, Haokun Liu, et al.*2020 · 281 citations*
7. **[An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization ↗](https://arxiv.org/abs/2002.07613) arXiv:2002.07613 · no summary yet**Yiqiu Shen et al.*2020 · 213 citations*
8. **[Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs](https://md.research.elamur.ai/free/en/papers/warstadt-2019-investigating-bert-s-knowledge-language/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Alex Warstadt, Yu Cao, Ioana Grosu, et al.*2019 · 179 citations*
9. **[Do Attention Heads in BERT Track Syntactic Dependencies? ↗](https://arxiv.org/abs/1911.12246) arXiv (Cornell University) · no summary yet**Phu Mon Htut et al.*2019 · 175 citations*
10. **[QuALITY: Question Answering with Long Input Texts, Yes!](https://md.research.elamur.ai/free/en/papers/pang-2022-quality-question-answering-long-input/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Richard Yuanzhe Pang, Alicia Parrish, Nitish Joshi, et al.*2022 · 167 citations*
11. [**Pretraining Language Models with Human Preferences arXiv:2302.08582**Tomasz Korbak, Kejian Shi, Angelica Chen, et al.*2023 · 121 citations*](https://md.research.elamur.ai/free/en/papers/korbak-2023-pretraining-language-models-human-preferences/)
12. **[Lessons from the Trenches on Reproducible Evaluation of Language Models ↗](https://arxiv.org/abs/2405.14782) arXiv:2405.14782 · no summary yet**Stella Biderman et al.*2024 · 99 citations*
13. **[jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models ↗](https://aclanthology.org/2020.acl-demos.15/) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · no summary yet**Yada Pruksachatkun et al.*2020 · 89 citations*
14. **[Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work? ↗](https://arxiv.org/abs/2005.00628) arXiv (Cornell University) · no summary yet**Yada Pruksachatkun et al.*2020 · 83 citations*
15. **[What Language Model to Train if You Have One Million GPU Hours? ↗](https://arxiv.org/abs/2210.15424) arXiv:2210.15424 · no summary yet**Teven Le Scao et al.*2022 · 73 citations*
16. **[English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too](https://md.research.elamur.ai/free/en/papers/phang-2020-english-intermediate-task-training-improves/) [Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL)](https://md.research.elamur.ai/free/en/venues/aacl/)**Jason Phang, Iacer Calixto, Phu Mon Htut, et al.*2020 · 70 citations*
17. **[SQuALITY: Building a Long-Document Summarization Dataset the Hard Way ↗](https://aclanthology.org/2022.emnlp-main.75/) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yet**Alex Wang et al.*2022 · 51 citations*
18. **[Comparing Test Sets with Item Response Theory ↗](https://aclanthology.org/2021.acl-long.92/) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yet**Clara Vania et al.*2021 · 47 citations*
19. **[What Do NLP Researchers Believe? Results of the NLP Community Metasurvey ↗](https://aclanthology.org/2023.acl-long.903/) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Julian Michael et al.*2023 · 40 citations*
20. **[Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers ↗](https://aclanthology.org/2021.blackboxnlp-1.42/) Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · no summary yet**Jason Phang, Haokun Liu, Samuel R. Bowman*2021 · 39 citations*
21. **[Globally-Aware Multiple Instance Classifier for Breast Cancer Screening ↗](https://doi.org/10.1007/978-3-030-32692-0_3) Lecture notes in computer science · no summary yet**Yiqiu Shen et al.*2019 · 38 citations*
22. [**Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs arXiv:2305.14279 · Transactions on Machine Learning Research (2024)**Angelica Chen, Jason Phang, Alicia Parrish, et al.*2023 · 25 citations*](https://md.research.elamur.ai/free/en/papers/chen-2023-two-failures-self-consistency-multi/)
23. **[Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair ↗](https://aclanthology.org/2022.dadc-1.8/) Proceedings of the First Workshop on Dynamic Adversarial Data Collection · no summary yet**Jason Phang et al.*2022 · 18 citations*
24. **[Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions ↗](https://aclanthology.org/2022.lnls-1.3/) Proceedings of the First Workshop on Learning with Natural Language Supervision · no summary yet**Alicia Parrish et al.*2022 · 13 citations*
25. **[Reducing False-Positive Biopsies using Deep Neural Networks that Utilize both Local and Global Image Context of Screening Mammograms ↗](https://doi.org/10.1007/s10278-021-00530-6) Journal of Imaging Informatics in Medicine · no summary yet**Nan Wu et al.*2021 · 12 citations*
26. **[Improving localization-based approaches for breast cancer screening exam classification ↗](https://arxiv.org/abs/1908.00615) arXiv (Cornell University) · no summary yet**Thibault Févry et al.*2019 · 10 citations*
27. **[Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions ↗](https://arxiv.org/abs/2210.10860) arXiv (Cornell University) · no summary yet**Alicia Parrish et al.*2022 · 6 citations*
28. **[Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms ↗](https://arxiv.org/abs/2009.09282) arXiv (Cornell University) · no summary yet**Nan Wu et al.*2020 · 3 citations*
29. **[Screening Mammogram Classification with Prior Exams ↗](https://arxiv.org/abs/1907.13057) arXiv (Cornell University) · no summary yet**Jungkyu Park et al.*2019*