pith. sign in

Suchin Gururangan

Identifiers

  • name variant Suchin Gururangan 0.60 · backfill

Papers (30)

  1. Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision cs.LG · 2025 · author #5
  2. Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder cs.CL · 2025 · author #4
  3. BTS: Harmonizing Specialized Experts into a Generalist LLM cs.CL · 2025 · author #11
  4. Self-Generated Critiques Boost Reward Modeling for Language Models cs.CL · 2024 · author #9
  5. The Llama 3 Herd of Models cs.AI · 2024 · author #193
  6. DataComp-LM: In search of the next generation of training sets for language models cs.LG · 2024 · author #17
  7. Language models scale reliably with over-training and on downstream tasks cs.CL · 2024 · author #4
  8. LESS: Selecting Influential Data for Targeted Instruction Tuning cs.CL · 2024 · author #3
  9. Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models cs.CL · 2024 · author #3
  10. AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters cs.CL · 2024 · author #2
  11. Time is Encoded in the Weights of Finetuned Language Models cs.CL · 2023 · author #2
  12. SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore cs.CL · 2023 · author #2
  13. Information Flow Control in Machine Learning through Modular Model Architecture cs.LG · 2023 · author #2
  14. Scaling Expert Language Models with Unsupervised Domain Discovery cs.CL · 2023 · author #1
  15. Editing Models with Task Arithmetic cs.LG · 2022 · author #4
  16. lo-fi: distributed fine-tuning without communication cs.LG · 2022 · author #2
  17. M2D2: A Massively Multi-domain Language Modeling Dataset cs.CL · 2022 · author #3
  18. Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models cs.CL · 2022 · author #2
  19. kNN-Prompt: Nearest Neighbor Zero-Shot Inference cs.CL · 2022 · author #3
  20. Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection cs.CL · 2022 · author #1
  21. Time Waits for No One! Analysis and Challenges of Temporal Misalignment cs.CL · 2021 · author #3
  22. Expected Validation Performance and Estimation of a Random Variable's Maximum cs.CL · 2021 · author #2
  23. DEMix Layers: Disentangling Domains for Modular Language Modeling cs.CL · 2021 · author #1
  24. All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text cs.CL · 2021 · author #5
  25. Detoxifying Language Models Risks Marginalizing Minority Voices cs.CL · 2021 · author #4
  26. RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models cs.CL · 2020 · author #2
  27. Don't Stop Pretraining: Adapt Language Models to Domains and Tasks cs.CL · 2020 · author #1
  28. Show Your Work: Improved Reporting of Experimental Results cs.LG · 2019 · author #2
  29. Variational Pretraining for Semi-supervised Text Classification cs.CL · 2019 · author #1
  30. Annotation Artifacts in Natural Language Inference Data cs.CL · 2018 · author #1

Mentions

  • 2502.14050 #4 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2411.16646 #9 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2502.00075 #11 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2401.10440 #3 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2308.04430 #2 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2306.03235 #2 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2401.06408 #2 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2403.08540 #4 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2402.04333 #3 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2312.13401 #2 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2212.04089 #4 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2303.14177 #1 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2210.11948 #2 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2205.13792 #3 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2210.07370 #3 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2208.03306 #2 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2111.07408 #3 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2201.10474 #1 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2110.00613 #2 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2108.05036 #1 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2107.00061 #5 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2104.06390 #4 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2004.10964 #1 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 1909.03004 #2 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 1906.02242 #1 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 1803.02324 #1 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2406.11794 #17 · arxiv_oai · confidence 0.70 Suchin Gururangan
  • 2009.11462 #2 · arxiv_oai · confidence 0.70 Suchin Gururangan

Frequent Coauthors