publications

publications in reversed chronological order. generated by jekyll-scholar.

Also see my Semantic Scholar and Google Scholar profiles.

† indicates core contributors

2024

  1. OLMoE: Open Mixture-of-Experts Language Models
    Niklas Muennighoff, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Jacob Daniel Morrison, and 19 more authors
    arXiv preprint, 2024
    PDF Code Model
    Press: VentureBeat, MarkTechPost, Analytics India Magazine
  2. OLMo: Accelerating the Science of Language Models
    Dirk Groeneveld, Iz Beltagy, Pete Walsh, Akshita Bhagia, Rodney Kinney, and 38 more authors
    ACL, 2024
    🏆 Best Theme Paper
    🏆 Geekwire Innovation of the Year
    PDF Code Website Model
    Press: Forbes, TechCrunch, Axios, GeekWire, VentureBeat, FastCompany
  3. Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
    Luca Soldaini†, Rodney Kinney†, Akshita Bhagia†, Dustin Schwenk†, David Atkinson, and 31 more authors
    ACL, 2024
    🏆 Best Resource Paper
    PDF Code Data
    Press: MarkTechPost, TechCrunch
  4. What’s In My Big Data?
    Yanai Elazar, Akshita Bhagia, Ian Magnusson, Abhilasha Ravichander, Dustin Schwenk, and 8 more authors
    ICLR, 2024
    Spotlight
    PDF Code Website
    Press: MarkTechPost

2023

  1. Paloma: A Benchmark for Evaluating Language Model Fit
    Ian Magnusson, Akshita Bhagia, Valentin Hofmann, Luca Soldaini, A. Jha, and 11 more authors
    In submission, 2023
    PDF Code Data

  2. Catwalk: A Unified Language Model Evaluation Framework for Many Datasets
    Dirk Groeneveld, Anas Awadalla, Iz Beltagy, Akshita Bhagia, Ian Magnusson, and 5 more authors
    arXiv preprint, 2023
    PDF Code

  3. Robust Tooling and New Resources for Large Language Model Evaluation via Catwalk (extended abstract)
    Kyle Richardson, Ian Magnusson, Oyvind Tafjord, Akshita Bhagia, Iz Beltagy, and 8 more authors
    GEM Workshop, EMNLP, 2023
    Code

  4. HINT: Hypernetwork Instruction Tuning for Efficient Zero-Shot Generalisation
    Hamish Ivison, Akshita Bhagia, Yizhong Wang, Hannaneh Hajishirzi, and Matthew Peters
    ACL, 2023
    PDF Code

2022

  1. Continued Pretraining for Better Zero- and Few-Shot Promptability
    Zhaofeng Wu, Robert L. Logan IV, Pete Walsh, Akshita Bhagia, Dirk Groeneveld, and 2 more authors
    EMNLP, 2022
    PDF Code

  2. On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
    Shruti Palaskar, Akshita Bhagia, Yonatan Bisk, Florian Metze, Alan W. Black, and 1 more author
    Findings of EMNLP, 2022
    PDF