Search Results for author: Andrew Beam

Found 7 papers, 4 papers with code

Large Language Models in Mental Health Care: a Scoping Review

no code implementations1 Jan 2024 Yining Hua, Fenglin Liu, Kailai Yang, Zehan Li, Yi-han Sheu, Peilin Zhou, Lauren V. Moran, Sophia Ananiadou, Andrew Beam

Objective: The growing use of large language models (LLMs) stimulates a need for a comprehensive review of their applications and outcomes in mental health care contexts.

Conformal Prediction with Large Language Models for Multi-Choice Question Answering

1 code implementation28 May 2023 Bhawesh Kumar, Charlie Lu, Gauri Gupta, Anil Palepu, David Bellamy, Ramesh Raskar, Andrew Beam

In this work, we explore how conformal prediction can be used to provide uncertainty quantification in language models for the specific task of multiple-choice question-answering.

Conformal Prediction Multiple-choice +2

Towards Reliable Zero Shot Classification in Self-Supervised Models with Conformal Prediction

no code implementations27 Oct 2022 Bhawesh Kumar, Anil Palepu, Rudraksh Tuwani, Andrew Beam

Self-supervised models trained with a contrastive loss such as CLIP have shown to be very powerful in zero-shot classification settings.

Classification Conformal Prediction +2

Coarse-to-Fine Memory Matching for Joint Retrieval and Classification

1 code implementation29 Nov 2020 Allen Schmaltz, Andrew Beam

We present a novel end-to-end language model for joint retrieval and classification, unifying the strengths of bi- and cross- encoders into a single language model via a coarse-to-fine memory matching search procedure for learning and inference.

Classification Fact Verification +3

Empirical Frequentist Coverage of Deep Learning Uncertainty Quantification Procedures

1 code implementation6 Oct 2020 Benjamin Kompa, Jasper Snoek, Andrew Beam

Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings.

Uncertainty Quantification

Exemplar Auditing for Multi-Label Biomedical Text Classification

no code implementations7 Apr 2020 Allen Schmaltz, Andrew Beam

These challenges are compounded for modalities such as text, where the feature space is very high-dimensional, and often contains considerable amounts of noise.

General Classification Multi-Label Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.