2.1k citations · 6.2k across the 128 of their papers we have counts for
137 papers
The SIMPLIFI Survey: Polarization of Dense Filaments with SOFIA III. Relative orientations of antenna temperature gradients with the magnetic field in the DR21 molecular cloud
Mark Heyer, Thushara G. S. Pillai, Jens Kauffmann +8
We investigate magnetohydrodynamic (MHD) turbulence in the DR21 molecular cloud using far infrared polarimetry from SOFIA HAWC+ and molecular spectroscopy from the Nobeyama 45~m te…
OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
Vineeth Dorna, Anmol Mekala, Wenlong Zhao +4
Robust unlearning is crucial for safely deploying large language models (LLMs) in environments where data privacy, model safety, and regulatory compliance must be ensured. Yet the…
Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
Daniel P. Jeong, Saurabh Garg, Zachary C. Lipton +1
Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs…
Online Data Collection for Efficient Semiparametric Inference
Shantanu Gupta, Zachary C. Lipton, David Childers
While many works have studied statistical data fusion, they typically assume that the various datasets are given in advance. However, in practice, estimation requires difficult dat…
The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
Jake Fawkes, Nic Fishman, Mel Andrews +1
Fairness metrics are a core tool in the fair machine learning literature (FairML), used to determine that ML models are, in some sense, "fair". Real-world data, however, are typica…
Towards characterizing the value of edge embeddings in Graph Neural Networks
Dhruv Rohatgi, Tanya Marwah, Zachary Chase Lipton +3
Graph neural networks (GNNs) are the dominant approach to solving machine learning problems defined over graphs. Despite much theoretical and empirical work in recent years, our un…
Failure Modes of LLMs for Causal Reasoning on Narratives
Khurram Yamin, Shantanu Gupta, Gaurav R. Ghosal +2
The ability to robustly identify causal relationships is essential for autonomous decision-making and adaptation to novel scenarios. However, accurately inferring causal structure…
LLM-Select: Feature Selection with Large Language Models
Daniel P. Jeong, Zachary C. Lipton, Pradeep Ravikumar
In this paper, we demonstrate a surprising capability of large language models (LLMs): given only input feature names and a description of a prediction task, they are capable of se…
Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends
Sanjana Ramprasad, Elisa Ferracane, Zachary C. Lipton
Recent advancements in large language models (LLMs) have considerably advanced the capabilities of summarization systems. However, they continue to face concerns about hallucinatio…
Understanding Hallucinations in Diffusion Models through Mode Interpolation
Sumukh K Aithal, Pratyush Maini, Zachary C. Lipton +1
Colloquially speaking, image generation models based upon diffusion processes are frequently said to exhibit "hallucinations," samples that could never occur in the training data.…
Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
Sachin Goyal, Pratyush Maini, Zachary C. Lipton +2
Vision-language models (VLMs) are trained for thousands of GPU hours on carefully curated web datasets. In recent times, data curation has gained prominence with several works deve…
Rethinking LLM Memorization through the Lens of Adversarial Compression
Avi Schwarzschild, Zhili Feng, Pratyush Maini +2
Large language models (LLMs) trained on web-scale datasets raise substantial concerns regarding permissible data usage. One major question is whether these models "memorize" all th…
Post-Hoc Reversal: Are We Selecting Models Prematurely?
Rishabh Ranjan, Saurabh Garg, Mrigank Raman +2
Trained models are often composed with post-hoc transforms such as temperature scaling (TS), ensembling and stochastic weight averaging (SWA) to improve performance, robustness, un…
Auditing Fairness under Unobserved Confounding
Yewon Byun, Dylan Sam, Michael Oberst +2
Many definitions of fairness or inequity involve unobservable causal quantities that cannot be directly estimated without strong assumptions. For instance, it is particularly diffi…
Evaluating the Factuality of Zero-shot Summarizers Across Varied Domains
Sanjana Ramprasad, Kundan Krishna, Zachary C Lipton +1
Recent work has shown that large language models (LLMs) are capable of generating summaries zero-shot (i.e., without explicit supervision) that, under human assessment, are often c…
GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
Kundan Krishna, Sanjana Ramprasad, Prakhar Gupta +3
LLMs can generate factually incorrect statements even when provided access to reference documents. Such errors can be dangerous in high-stakes applications (e.g., document-grounded…
TOFU: A Task of Fictitious Unlearning for LLMs
Pratyush Maini, Zhili Feng, Avi Schwarzschild +2
Large language models trained on massive corpora of data from the web can memorize and reproduce sensitive or private data raising both legal and ethical concerns. Unlearning, or t…
Red-Teaming for Generative AI: Silver Bullet or Security Theater?
Michael Feffer, Anusha Sinha, Wesley Hanwen Deng +2
In response to rising concerns surrounding the safety, security, and trustworthiness of Generative AI (GenAI) models, practitioners and regulators alike have pointed to AI red-team…
Perspectives on the State and Future of Deep Learning - 2023
Micah Goldblum, Anima Anandkumar, Richard Baraniuk +7
The goal of this series is to chronicle opinions and issues in the field of machine learning as they stand today and as they change over time. The plan is to host this survey perio…
Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift
Saurabh Garg, Amrith Setlur, Zachary Chase Lipton +3
Self-training and contrastive learning have emerged as leading techniques for incorporating unlabeled data, both under distribution shift (unsupervised domain adaptation) and when…
Deep Equilibrium Based Neural Operators for Steady-State PDEs
Tanya Marwah, Ashwini Pokle, J. Zico Kolter +3
Data-driven machine learning approaches are being increasingly used to solve partial differential equations (PDEs). They have shown particularly striking successes when training an…
MoCo-Transfer: Investigating out-of-distribution contrastive learning for limited-data domains
Yuwen Chen, Helen Zhou, Zachary C. Lipton
Medical imaging data is often siloed within hospitals, limiting the amount of data available for specialized model development. With limited in-domain data, one might hope to lever…
Reading Between the Mud: A Challenging Motorcycle Racer Number Dataset
Jacob Tyo, Youngseog Chung, Motolani Olarinre +1
This paper introduces the off-road motorcycle Racer number Dataset (RnD), a new challenging dataset for optical character recognition (OCR) research. RnD contains 2,411 images from…
MUDD: A New Re-Identification Dataset with Efficient Annotation for Off-Road Racers in Extreme Conditions
Jacob Tyo, Motolani Olarinre, Youngseog Chung +1
Re-identifying individuals in unconstrained environments remains an open challenge in computer vision. We introduce the Muddy Racer re-IDentification Dataset (MUDD), the first larg…