429 citations · 665 across the 28 of their papers we have counts for
14 papers · 1 filter
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
Yue Huang, Hang Hua, Yujun Zhou +11
While LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm, since certain risks can lead to…
Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
Dennis Wei, Inkit Padhi, Soumya Ghosh +3
Training data attribution (TDA) is concerned with understanding model behavior in terms of the training data. This paper draws attention to the common setting where one has access…
Programming Refusal with Conditional Activation Steering
Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy +4
LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscrimina…
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
Swanand Ravindra Kadhe, Farhan Ahmed, Dennis Wei +2
Large language models (LLMs) have shown to pose social and ethical risks such as generating toxic language or facilitating malicious use of hazardous knowledge. Machine unlearning…
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor +35
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (trai…
Auditing and Generating Synthetic Data with Controllable Trust Trade-offs
Brian Belgodere, Pierre Dognin, Adam Ivankay +11
Real-world data often exhibits bias, imbalance, and privacy risks. Synthetic datasets have emerged to address these issues. This paradigm relies on generative AI models to generate…
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
Prasanna Sattigeri, Soumya Ghosh, Inkit Padhi +2
In consequential decision-making applications, mitigating unwanted biases in machine learning models that yield systematic disadvantage to members of groups delineated by sensitive…
Cloud-Based Real-Time Molecular Screening Platform with MolFormer
Brian Belgodere, Vijil Chenthamarakshan, Payel Das +9
With the prospect of automating a number of chemical tasks with high fidelity, chemical language processing models are emerging at a rapid speed. Here, we present a cloud-based rea…
Accelerating Material Design with the Generative Toolkit for Scientific Discovery
Matteo Manica, Jannis Born, Joris Cadow +21
With the growing availability of data within various scientific domains, generative models hold enormous potential to accelerate scientific discovery. They harness powerful represe…
Large-Scale Chemical Language Representations Capture Molecular Structure and Properties
Jerret Ross, Brian Belgodere, Vijil Chenthamarakshan +3
Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design. Various supervised machine…
Tabular Transformers for Modeling Multivariate Time Series
Inkit Padhi, Yair Schiff, Igor Melnyk +6
Tabular datasets are ubiquitous in data science applications. Given their importance, it seems natural to apply state-of-the-art deep learning algorithms in order to fully unlock t…
Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics
Payel Das, Tom Sercu, Kahini Wadhawan +12
De novo therapeutic design is challenged by a vast chemical repertoire and multiple constraints, e.g., high broad-spectrum potency and low toxicity. We propose CLaSS (Controlled La…
CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
Vijil Chenthamarakshan, Payel Das, Samuel C. Hoffman +8
The novel nature of SARS-CoV-2 calls for the development of efficient de novo drug design approaches. In this study, we propose an end-to-end framework, named CogMol (Controlled Ge…
Sobolev Independence Criterion
Youssef Mroueh, Tom Sercu, Mattia Rigotti +2
We propose the Sobolev Independence Criterion (SIC), an interpretable dependency measure between a high dimensional random variable X and a response variable Y . SIC decomposes to…