Neel Guha

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., Ré, 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

• THE STATE STATUTES PROJECT WISCONSIN LAW REVIEW Guha, N., Zambrano, D. 2024

  View details for DOI 10.59015/wlr.KMEM2466

  View details for Web of Science ID 001368041000008

• PRIVATE ENFORCEMENT IN THE STATES UNIVERSITY OF PENNSYLVANIA LAW REVIEW Zambrano, D. A., Guha, N., Peters, A., Xia, J. 2023; 172 (1)

  View details for Web of Science ID 001208959900003

• 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

  View details for Web of Science ID 001003618200006

• 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

  View details for DOI 10.1145/3594536.3595142

  View details for Web of Science ID 001139079400015

• 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

  View details for Web of Science ID 001220818804023

• 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

  View details for Web of Science ID 001226352803033