56 citations · 57 across the 13 of their papers we have counts for
14 papers
Continual Learning without Continual Training
Nikita Narayanan, Ritham Majumdarr, Sonali Parbhoo
Continual learning requires models to adapt to new domains and new classes while retaining prior knowledge. Many existing methods rely on continued optimization, using regularizati…
Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
Amartya Roy, Sonali Parbhoo
Causal discovery is a cornerstone of scientific reasoning, yet whether large language models can perform it reliably remains an open question. Recent benchmarks show that even fine…
Causal methods for LLM development and evaluation
Dennis Frauen, Marie Brockschmidt, Konstantin Hess +10
Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and evaluation pipelines. Here,…
Causal Machine Learning Is Not a Panacea: A Roadmap for Observational Causal Inference in Health
Donna Tjandra, Trenton Chang, Sonali Parbhoo +8
Objective: The growing availability of large-scale observational clinical datasets and challenges in conducting randomized controlled trials have spurred enthusiasm in using causal…
The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
Matthieu Bou, Nyal Patel, Arjun Jagota +2
The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge. While Inverse Reinforce…
Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
Nyal Patel, Matthieu Bou, Arjun Jagota +2
Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posi…
Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models
Anish Narain, Ritam Majumdar, Nikita Narayanan +2
Large, publicly available clinical datasets have emerged as a novel resource for understanding disease heterogeneity and to explore personalization of therapy. These datasets are d…
Causal Bayesian Optimization with Unknown Graphs
Jean Durand, Yashas Annadani, Stefan Bauer +1
Causal Bayesian Optimization (CBO) is a methodology designed to optimize an outcome variable by leveraging known causal relationships through targeted interventions. Traditional CB…
Do regularization methods for shortcut mitigation work as intended?
Haoyang Hong, Ioanna Papanikolaou, Sonali Parbhoo
Mitigating shortcuts, where models exploit spurious correlations in training data, remains a significant challenge for improving generalization. Regularization methods have been pr…
Feature Importance Depends on Properties of the Data: Towards Choosing the Correct Explanations for Your Data and Decision Trees based Models
Célia Wafa Ayad, Thomas Bonnier, Benjamin Bosch +2
In order to ensure the reliability of the explanations of machine learning models, it is crucial to establish their advantages and limits and in which case each of these methods ou…
Concept-driven Off Policy Evaluation
Ritam Majumdar, Jack Teversham, Sonali Parbhoo
Evaluating off-policy decisions using batch data poses significant challenges due to limited sample sizes leading to high variance. To improve Off-Policy Evaluation (OPE), we must…
Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning
Jared Joselowitz, Ritam Majumdar, Arjun Jagota +4
Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and dec…
Adaptive Experimental Design for Intrusion Data Collection
Kate Highnam, Zach Hanif, Ellie Van Vogt +3
Intrusion research frequently collects data on attack techniques currently employed and their potential symptoms. This includes deploying honeypots, logging events from existing de…
Real-time Prediction of COVID-19 related Mortality using Electronic Health Records
Patrick Schwab, Arash Mehrjou, Sonali Parbhoo +5
Coronavirus Disease 2019 (COVID-19) is an emerging respiratory disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) with rapid human-to-human transmis…