3 citations · 5 across the 12 of their papers we have counts for
15 papers
Exploring The Empirical Privacy Landscape of Synthetic Data
Zihao Zhao, Avi Schwarzschild, Casey Meehan +3
Methods for training language models on sensitive data differ in how they balance capability gains against the risk of leaking private information. In this paper, we present a cont…
When Should We Introduce Safety Interventions During Pretraining?
Dylan Sam, Sachin Goyal, Pratyush Maini +2
Prior work has shown that safety interventions applied during pretraining, such as removing and rephrasing harmful content, can substantially improve the robustness of the resultin…
Evaluating Language Model Reasoning about Confidential Information
Dylan Sam, Alexander Robey, Andy Zou +2
As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concer…
Safety Pretraining: Toward the Next Generation of Safe AI
Pratyush Maini, Sachin Goyal, Dylan Sam +7
As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment m…
Analyzing Similarity Metrics for Data Selection for Language Model Pretraining
Dylan Sam, Ayan Chakrabarti, Afshin Rostamizadeh +3
Measuring similarity between training examples is critical for curating high-quality and diverse pretraining datasets for language models. However, similarity is typically computed…
Predicting the Performance of Black-box LLMs through Follow-up Queries
Dylan Sam, Marc Finzi, J. Zico Kolter
Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This…
Finetuning CLIP to Reason about Pairwise Differences
Dylan Sam, Devin Willmott, Joao D. Semedo +1
Vision-language models (VLMs) such as CLIP are trained via contrastive learning between text and image pairs, resulting in aligned image and text embeddings that are useful for man…
Computing Low-Entropy Couplings for Large-Support Distributions
Samuel Sokota, Dylan Sam, Christian Schroeder de Witt +3
Minimum-entropy coupling (MEC) -- the process of finding a joint distribution with minimum entropy for given marginals -- has applications in areas such as causality and steganogra…
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…
Bayesian Neural Networks with Domain Knowledge Priors
Dylan Sam, Rattana Pukdee, Daniel P. Jeong +2
Bayesian neural networks (BNNs) have recently gained popularity due to their ability to quantify model uncertainty. However, specifying a prior for BNNs that captures relevant doma…
Understanding prompt engineering may not require rethinking generalization
Victor Akinwande, Yiding Jiang, Dylan Sam +1
Zero-shot learning in prompted vision-language models, the practice of crafting prompts to build classifiers without an explicit training process, has achieved impressive performan…
Learning with Explanation Constraints
Rattana Pukdee, Dylan Sam, J. Zico Kolter +2
As larger deep learning models are hard to interpret, there has been a recent focus on generating explanations of these black-box models. In contrast, we may have apriori explanati…
Improving self-supervised representation learning via sequential adversarial masking
Dylan Sam, Min Bai, Tristan McKinney +1
Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision. Howeve…
Losses over Labels: Weakly Supervised Learning via Direct Loss Construction
Dylan Sam, J. Zico Kolter
Owing to the prohibitive costs of generating large amounts of labeled data, programmatic weak supervision is a growing paradigm within machine learning. In this setting, users desi…
Label Propagation with Weak Supervision
Rattana Pukdee, Dylan Sam, Maria-Florina Balcan +1
Semi-supervised learning and weakly supervised learning are important paradigms that aim to reduce the growing demand for labeled data in current machine learning applications. In…