706 citations · 749 across the 20 of their papers we have counts for
22 papers
When Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free Evaluation
Xiang Zhang, Lovedeep Gondara, Jekaterina Novikova
Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an implicit assumption that consisten…
The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express
Lovedeep Gondara, Jekaterina Novikova, Sagarika Suresh +2
When an LLM judge filters instruction-tuning data, its scoring format (binary verdict, 1--5 rating, 0--100 score, or comparison) is rarely justified or ablated. Holding the candida…
Learning from Lost Provenance: Multiple Instance Learning for Cancer Registry Tumor Group Classification
Leonard Ruocco, Jonathan Simkin, Lovedeep Gondara +2
Modernizing cancer registries with deep learning is opening new opportunities to automate labor-intensive tasks such as the coding of pathology reports. However, progress is constr…
A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models
Nima Eshraghi, Lovedeep Gondara, Yuqing Huang +5
Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning, but standard methods apply the steering si…
Supervised Learning Objectives for High-Dimensional Treatment Effects
Nikita Dhawan, Arnav Paruthi, Andrew Kim +3
Predicting the effect of interventions with many possible variations, e.g., therapeutic content that affects mental health outcomes or an earnings call transcript that drives movem…
De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules
Keerat Guliani, Deepkamal Gill, David Landsman +3
Regulatory documents encode legally binding obligations that LLM-based systems must respect. Yet converting dense, hierarchically structured legal text into machine-readable rules…
Adapting Natural Language Processing Models Across Jurisdictions: A pilot Study in Canadian Cancer Registries
Jonathan Simkin, Lovedeep Gondara, Zeeshan Rizvi +5
Population-based cancer registries depend on pathology reports as their primary diagnostic source, yet manual abstraction is resource-intensive and contributes to delays in cancer…
Beyond Ethics: How Inclusive Innovation Drives Economic Returns in Medical AI
Balagopal Unnikrishnan, Ariel Guerra Adames, Amin Adibi +10
While ethical arguments for fairness in healthcare AI are well-established, the economic and strategic value of inclusive design remains underexplored. This perspective introduces…
Bridging AI Innovation and Healthcare Needs: Lessons Learned from Incorporating Modern NLP at The BC Cancer Registry
Lovedeep Gondara, Gregory Arbour, Raymond Ng +2
Automating data extraction from clinical documents offers significant potential to improve efficiency in healthcare settings, yet deploying Natural Language Processing (NLP) soluti…
Leveraging Language Models for Automated Patient Record Linkage
Mohammad Beheshti, Lovedeep Gondara, Iris Zachary
Objective: Healthcare data fragmentation presents a major challenge for linking patient data, necessitating robust record linkage to integrate patient records from diverse sources.…
Small or Large? Zero-Shot or Finetuned? Guiding Language Model Choice for Specialized Applications in Healthcare
Lovedeep Gondara, Jonathan Simkin, Graham Sayle +3
This study aims to guide language model selection by investigating: 1) the necessity of finetuning versus zero-shot usage, 2) the benefits of domain-adjacent versus generic pretrai…
ELM: A Hybrid Ensemble of Language Models for Automated Tumor Group Classification in Population-Based Cancer Registries
Lovedeep Gondara, Jonathan Simkin, Shebnum Devji +2
Background: Population-based cancer registries (PBCRs) manually extract data from unstructured pathology reports, a labor-intensive process where assigning reports to tumor groups…
A Clinical Trial Design Approach to Auditing Language Models in Healthcare Setting
Lovedeep Gondara, Jonathan Simkin
We present an audit mechanism for language models, with a focus on models deployed in the healthcare setting. Our proposed mechanism takes inspiration from clinical trial design wh…
Differentially Private Ensemble Classifiers for Data Streams
Lovedeep Gondara, Ke Wang, Ricardo Silva Carvalho
Learning from continuous data streams via classification/regression is prevalent in many domains. Adapting to evolving data characteristics (concept drift) while protecting data ow…
The Differentially Private Lottery Ticket Mechanism
Lovedeep Gondara, Ke Wang, Ricardo Silva Carvalho
We propose the differentially private lottery ticket mechanism (DPLTM). An end-to-end differentially private training paradigm based on the lottery ticket hypothesis. Using "high-q…
Differentially Private Survival Function Estimation
Lovedeep Gondara, Ke Wang
Survival function estimation is used in many disciplines, but it is most common in medical analytics in the form of the Kaplan-Meier estimator. Sensitive data (patient records) is…
Recovering Loss to Followup Information Using Denoising Autoencoders
Lovedeep Gondara, Ke Wang
Loss to followup is a significant issue in healthcare and has serious consequences for a study's validity and cost. Methods available at present for recovering loss to followup inf…
MIDA: Multiple Imputation using Denoising Autoencoders
Lovedeep Gondara, Ke Wang
Missing data is a significant problem impacting all domains. State-of-the-art framework for minimizing missing data bias is multiple imputation, for which the choice of an imputati…
Detecting Adversarial Samples Using Density Ratio Estimates
Lovedeep Gondara
Machine learning models, especially based on deep architectures are used in everyday applications ranging from self driving cars to medical diagnostics. It has been shown that such…
CrowdMI: Multiple Imputation via Crowdsourcing
Lovedeep Gondara
Can humans impute missing data with similar proficiency as machines? This is the question we aim to answer in this paper. We present a novel idea of converting observations with mi…
Medical image denoising using convolutional denoising autoencoders
Lovedeep Gondara
Image denoising is an important pre-processing step in medical image analysis. Different algorithms have been proposed in past three decades with varying denoising performances. Mo…
Classifier comparison using precision
Lovedeep Gondara
New proposed models are often compared to state-of-the-art using statistical significance testing. Literature is scarce for classifier comparison using metrics other than accuracy.…