Suchin Gururangan

55 papers A* 11Journal 31Unranked 12
YearRankTypeTitle / Venue / Authors
2025 A* conf
BTS: Harmonizing Specialized Experts into a Generalist LLM.
EMNLP
Qizhen Zhang, Prajjwal Bhargava, Chloe Bi, Chris X. Cai, Jakob Nicolaus Foerster, Jeremy Fu, Punit Singh Koura, Ruan Silva, Sheng Shen, Emily Dinan, Suchin Gururangan, Mike Lewis
2025 J jnl
BTS: Harmonizing Specialized Experts into a Generalist LLM.
CoRR
Qizhen Zhang, Prajjwal Bhargava, Chloe Bi, Chris X. Cai, Jakob N. Foerster, Jeremy Fu, Punit Singh Koura, Ruan Silva, Sheng Shen, Emily Dinan, Suchin Gururangan, Mike Lewis
2025 J jnl
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision.
CoRR
Dulhan Jayalath, Shashwat Goel, Thomas Foster, Parag Jain, Suchin Gururangan, Cheng Zhang, Anirudh Goyal, Alan Schelten
2025 J jnl
Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder.
CoRR
Xianjun Yang, Shaoliang Nie, Lijuan Liu, Suchin Gururangan, Ujjwal Karn, Rui Hou, Madian Khabsa, Yuning Mao
2025 A* conf
Language models scale reliably with over-training and on downstream tasks.
ICLR
Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, Suchin Gururangan, Mitchell Wortsman, Rulin Shao, Jean Mercat, Alex Fang, Jeffrey Li, Sedrick Keh, Rui Xin, Marianna Nezhurina, Igor Vasiljevic, Luca Soldaini, Jenia Jitsev, Alex Dimakis, Gabriel Ilharco, Pang Wei Koh, Shuran Song, Thomas Kollar, et al.
2025 J jnl
Rethinking Thinking Tokens: LLMs as Improvement Operators.
CoRR
Lovish Madaan, Aniket Didolkar, Suchin Gururangan, John Quan, Ruan Silva, Ruslan Salakhutdinov, Manzil Zaheer, Sanjeev Arora, Anirudh Goyal
2025 — conf
Self-Generated Critiques Boost Reward Modeling for Language Models.
NAACL (Long Papers)
Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou
2024 — conf
AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters.
ACL (1)
Li Lucy, Suchin Gururangan, Luca Soldaini, Emma Strubell, David Bamman, Lauren F. Klein, Jesse Dodge
2024 J jnl
AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters.
CoRR
Li Lucy, Suchin Gururangan, Luca Soldaini, Emma Strubell, David Bamman, Lauren F. Klein, Jesse Dodge
2024 A* conf
Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models.
EMNLP
Terra Blevins, Tomasz Limisiewicz, Suchin Gururangan, Margaret Li, Hila Gonen, Noah A. Smith, Luke Zettlemoyer
2024 J jnl
Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models.
CoRR
Terra Blevins, Tomasz Limisiewicz, Suchin Gururangan, Margaret Li, Hila Gonen, Noah A. Smith, Luke Zettlemoyer
2024 — —
Data-Centric Methods for Decentralizing Large Language Models
Suchin Gururangan
2024 A* conf
DataComp-LM: In search of the next generation of training sets for language models.
NeurIPS
Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Kumar Guha, Sedrick Scott Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee F. Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M. Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Raghavi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alex Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar
2024 J jnl
DataComp-LM: In search of the next generation of training sets for language models.
CoRR
Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Kumar Guha, Sedrick Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee F. Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M. Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Raghavi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alexandros G. Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar
2024 A* conf
Information Flow Control in Machine Learning through Modular Model Architecture.
USENIX Security Symposium
Trishita Tiwari, Suchin Gururangan, Chuan Guo, Weizhe Hua, Sanjay Kariyappa, Udit Gupta, Wenjie Xiong, Kiwan Maeng, Hsien-Hsin S. Lee, G. Edward Suh
2024 A* conf
LESS: Selecting Influential Data for Targeted Instruction Tuning.
ICML
Mengzhou Xia, Sadhika Malladi, Suchin Gururangan, Sanjeev Arora, Danqi Chen
2024 J jnl
LESS: Selecting Influential Data for Targeted Instruction Tuning.
CoRR
Mengzhou Xia, Sadhika Malladi, Suchin Gururangan, Sanjeev Arora, Danqi Chen
2024 J jnl
Language models scale reliably with over-training and on downstream tasks.
CoRR
Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, Suchin Gururangan, Mitchell Wortsman, Rulin Shao, Jean Mercat, Alex Fang, Jeffrey Li, Sedrick Keh, Rui Xin, Marianna Nezhurina, Igor Vasiljevic, Jenia Jitsev, Alexandros G. Dimakis, Gabriel Ilharco, Shuran Song, Thomas Kollar, Yair Carmon, Achal Dave, Reinhard Heckel, Niklas Muennighoff, Ludwig Schmidt
2024 A* conf
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore.
ICLR
Sewon Min, Suchin Gururangan, Eric Wallace, Weijia Shi, Hannaneh Hajishirzi, Noah A. Smith, Luke Zettlemoyer
2024 J jnl
Self-Generated Critiques Boost Reward Modeling for Language Models.
CoRR
Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou
2024 — conf
Time is Encoded in the Weights of Finetuned Language Models.
ACL (1)
Kai Nylund, Suchin Gururangan, Noah A. Smith
2023 J jnl
Information Flow Control in Machine Learning through Modular Model Architecture.
CoRR
Trishita Tiwari, Suchin Gururangan, Chuan Guo, Weizhe Hua, Sanjay Kariyappa, Udit Gupta, Wenjie Xiong, Kiwan Maeng, Hsien-Hsin S. Lee, G. Edward Suh
2023 J jnl
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore.
CoRR
Sewon Min, Suchin Gururangan, Eric Wallace, Hannaneh Hajishirzi, Noah A. Smith, Luke Zettlemoyer
2023 J jnl
Scaling Expert Language Models with Unsupervised Domain Discovery.
CoRR
Suchin Gururangan, Margaret Li, Mike Lewis, Weijia Shi, Tim Althoff, Noah A. Smith, Luke Zettlemoyer
2023 J jnl
Time is Encoded in the Weights of Finetuned Language Models.
CoRR
Kai Nylund, Suchin Gururangan, Noah A. Smith
2023 J jnl
lo-fi: distributed fine-tuning without communication.
Trans. Mach. Learn. Res.
Mitchell Wortsman, Suchin Gururangan, Shen Li, Ali Farhadi, Ludwig Schmidt, Michael G. Rabbat, Ari S. Morcos
2022 J jnl
Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models.
CoRR
Margaret Li, Suchin Gururangan, Tim Dettmers, Mike Lewis, Tim Althoff, Noah A. Smith, Luke Zettlemoyer
2022 — conf
DEMix Layers: Disentangling Domains for Modular Language Modeling.
NAACL-HLT
Suchin Gururangan, Mike Lewis, Ari Holtzman, Noah A. Smith, Luke Zettlemoyer
2022 J jnl
Editing Models with Task Arithmetic.
CoRR
Gabriel Ilharco, Marco Túlio Ribeiro, Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, Ali Farhadi
2022 A* conf
M2D2: A Massively Multi-Domain Language Modeling Dataset.
EMNLP
Machel Reid, Victor Zhong, Suchin Gururangan, Luke Zettlemoyer
2022 J jnl
M2D2: A Massively Multi-domain Language Modeling Dataset.
CoRR
Machel Reid, Victor Zhong, Suchin Gururangan, Luke Zettlemoyer
2022 A* conf
Nearest Neighbor Zero-Shot Inference.
EMNLP
Weijia Shi, Julian Michael, Suchin Gururangan, Luke Zettlemoyer
2022 J jnl
Nearest Neighbor Zero-Shot Inference.
CoRR
Weijia Shi, Julian Michael, Suchin Gururangan, Luke Zettlemoyer
2022 — conf
Time Waits for No One! Analysis and Challenges of Temporal Misalignment.
NAACL-HLT
Kelvin Luu, Daniel Khashabi, Suchin Gururangan, Karishma Mandyam, Noah A. Smith
2022 A* conf
Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection.
EMNLP
Suchin Gururangan, Dallas Card, Sarah K. Dreier, Emily K. Gade, Leroy Z. Wang, Zeyu Wang, Luke Zettlemoyer, Noah A. Smith
2022 J jnl
Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection.
CoRR
Suchin Gururangan, Dallas Card, Sarah K. Dreier, Emily K. Gade, Leroy Z. Wang, Zeyu Wang, Luke Zettlemoyer, Noah A. Smith
2022 J jnl
lo-fi: distributed fine-tuning without communication.
CoRR
Mitchell Wortsman, Suchin Gururangan, Shen Li, Ali Farhadi, Ludwig Schmidt, Michael G. Rabbat, Ari S. Morcos
2021 — conf
All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text.
ACL/IJCNLP (1)
Elizabeth Clark, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan, Noah A. Smith
2021 J jnl
All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text.
CoRR
Elizabeth Clark, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan, Noah A. Smith
2021 J jnl
DEMix Layers: Disentangling Domains for Modular Language Modeling.
CoRR
Suchin Gururangan, Mike Lewis, Ari Holtzman, Noah A. Smith, Luke Zettlemoyer
2021 — conf
Detoxifying Language Models Risks Marginalizing Minority Voices.
NAACL-HLT
Albert Xu, Eshaan Pathak, Eric Wallace, Suchin Gururangan, Maarten Sap, Dan Klein
2021 J jnl
Detoxifying Language Models Risks Marginalizing Minority Voices.
CoRR
Albert Xu, Eshaan Pathak, Eric Wallace, Suchin Gururangan, Maarten Sap, Dan Klein
2021 — conf
Expected Validation Performance and Estimation of a Random Variable's Maximum.
EMNLP (Findings)
Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. Smith
2021 J jnl
Expected Validation Performance and Estimation of a Random Variable's Maximum.
CoRR
Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. Smith
2021 J jnl
Time Waits for No One! Analysis and Challenges of Temporal Misalignment.
CoRR
Kelvin Luu, Daniel Khashabi, Suchin Gururangan, Karishma Mandyam, Noah A. Smith
2020 A* conf
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks.
ACL
Suchin Gururangan, Ana Marasovic, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, Noah A. Smith
2020 J jnl
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks.
CoRR
Suchin Gururangan, Ana Marasovic, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, Noah A. Smith
2020 — conf
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.
EMNLP (Findings)
Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, Noah A. Smith
2020 J jnl
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.
CoRR
Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, Noah A. Smith
2019 — conf
Show Your Work: Improved Reporting of Experimental Results.
EMNLP/IJCNLP (1)
Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. Smith
2019 J jnl
Show Your Work: Improved Reporting of Experimental Results.
CoRR
Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. Smith
2019 — conf
Variational Pretraining for Semi-supervised Text Classification.
ACL (1)
Suchin Gururangan, Tam Dang, Dallas Card, Noah A. Smith
2019 J jnl
Variational Pretraining for Semi-supervised Text Classification.
CoRR
Suchin Gururangan, Tam Dang, Dallas Card, Noah A. Smith
2018 — conf
Annotation Artifacts in Natural Language Inference Data.
NAACL-HLT (2)
Suchin Gururangan, Swabha Swayamdipta, Omer Levy, Roy Schwartz, Samuel R. Bowman, Noah A. Smith
2018 J jnl
Annotation Artifacts in Natural Language Inference Data.
CoRR
Suchin Gururangan, Swabha Swayamdipta, Omer Levy, Roy Schwartz, Samuel R. Bowman, Noah A. Smith