All Publications


  • Prospector Heads: Generalized Feature Attribution for Large Models & Data. ArXiv Machiraju, G., Derry, A., Desai, A., Guha, N., Karimi, A. H., Zou, J., Altman, R. B., RĂ©, C., Mallick, P. 2024

    Abstract

    Feature attribution, the ability to localize regions of the input data that are relevant for classification, is an important capability for ML models in scientific and biomedical domains. Current methods for feature attribution, which rely on "explaining" the predictions of end-to-end classifiers, suffer from imprecise feature localization and are inadequate for use with small sample sizes and high-dimensional datasets due to computational challenges. We introduce prospector heads, an efficient and interpretable alternative to explanation-based attribution methods that can be applied to any encoder and any data modality. Prospector heads generalize across modalities through experiments on sequences (text), images (pathology), and graphs (protein structures), outperforming baseline attribution methods by up to 26.3 points in mean localization AUPRC. We also demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data. Through their high performance, flexibility, and generalizability, prospectors provide a framework for improving trust and transparency for ML models in complex domains.

    View details for PubMedID 38947933

    View details for PubMedCentralID PMC11213143

  • Understanding Liability Risk from Using Health Care Artificial Intelligence Tools. The New England journal of medicine Mello, M. M., Guha, N. 2024; 390 (3): 271-278

    View details for DOI 10.1056/NEJMhle2308901

    View details for PubMedID 38231630

  • PRIVATE ENFORCEMENT IN THE STATES UNIVERSITY OF PENNSYLVANIA LAW REVIEW Zambrano, D. A., Guha, N., Peters, A., Xia, J. 2023; 172 (1)
  • ChatGPT and Physicians' Malpractice Risk. JAMA health forum Mello, M. M., Guha, N. 2023; 4 (5): e231938

    Abstract

    This JAMA Forum discusses the possibilities, limitations, and risks of physician use of large language models (such as ChatGPT) along with the improvements required to improve the accuracy of the technology.

    View details for DOI 10.1001/jamahealthforum.2023.1938

    View details for PubMedID 37200013

  • Gamesmanship in Modern Discovery Tech LEGAL TECH AND THE FUTURE OF CIVIL JUSTICE Guha, N., Henderson, P., Zambrano, D. A., Engstrom, D. F. 2023: 112-132
  • Don't Use a Cannon to Kill a Fly: An Efficient Cascading Pipeline for Long Documents Li, Z., Guha, N., Nyarko, J., ACM ASSOC COMPUTING MACHINERY. 2023: 141-147
  • Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification Guha, N., Chen, M. F., Bhatia, K., Mirhoseini, A., Sala, F., Re, C., Oh, A., Neumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2023
  • LEGALBENCH: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models Guha, N., Nyarko, J., Ho, D. E., Re, C., Chilton, A., Narayana, A., Chohlas-Wood, A., Peters, A., Waldon, B., Rockmore, D. N., Zambrano, D., Talisman, D., Hoque, E., Surani, F., Fagan, F., Sarfaty, G., Dickinson, G. M., Porat, H., Hegland, J., Wu, J., Nudell, J., Niklaus, J., Nay, J., Choi, J. H., Tobia, K., Hagan, M., Ma, M., Livermore, M., Rasumov-Rahe, N., Holzenberger, N., Kolt, N., Henderson, P., Rehaag, S., Goel, S., Gao, S., Williams, S., Gandhi, S., Zur, T., Iyer, V., Li, Z., Oh, A., Neumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2023