7 papers
FinRT: Distilling Adaptive Red-Teaming Strategies into Reusable Adversarial Generators in Consumer Finance
Rikhiya Ghosh, Himanshu Kumar, Sriram Venkatapathy +3
In regulated industries like consumer finance, seemingly harmless user queries can exploit large language model vulnerabilities, triggering safety failures and pushing responses da…
MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter
Vignesh Nagarajan, Sriram Venkatapathy
A radiologist reading a model's output faces two problems. The model returns a number and no reason, and any system that turns that number into readable prose can quietly add claim…
Workspace Topology as an Attack Vector in Agentic Coding Assistants
Alexandre G. R. Day, Pradeep Yadlapalli, Sriram Venkatapathy +9
Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code. This opens up a risk of malicious c…
CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization
Brihi Joshi, Sriram Venkatapathy, Mohit Bansal +2
Evaluating creative text such as human-written stories using language models has always been a challenging task -- owing to the subjectivity of multi-annotator ratings. To mimic th…
Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations
Kuan-Hao Huang, Varun Iyer, Anoop Kumar +3
Syntactically controlled paraphrase generation has become an emerging research direction in recent years. Most existing approaches require annotated paraphrase pairs for training a…
Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks
Ansel MacLaughlin, Jwala Dhamala, Anoop Kumar +3
Neural Architecture Search (NAS) methods, which automatically learn entire neural model or individual neural cell architectures, have recently achieved competitive or state-of-the-…
Assisting Composition of Email Responses: a Topic Prediction Approach
Spandana Gella, Marc Dymetman, Jean Michel Renders +1
We propose an approach for helping agents compose email replies to customer requests. To enable that, we use LDA to extract latent topics from a collection of email exchanges. We t…