706 citations · 749 across the 20 of their papers we have counts for
7 papers · 1 filter
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…