Jay Pujara

Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources

2021 · arXiv (Cornell University)

Warning: this paper contains content that may be offensive or upsetting. Numerous natural language processing models have tried injecting commonsense by using the ConceptNet knowledge base to improve performance on different tasks. ConceptNet, however, is …

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking

2024 · arXiv (Cornell University)

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been …

LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance Reasoning

2025 · arXiv (Cornell University)

High-assurance reasoning, particularly in critical domains such as law and medicine, requires conclusions that are accurate, verifiable, and explicitly grounded in evidence. This reasoning relies on premises codified from rules, statutes, and contracts, inherently involving …

User Preferences for Hybrid Explanations

2017

Hybrid recommender systems combine several different sources of information to generate recommendations. These systems demonstrate improved accuracy compared to single-source recommendation strategies. However, hybrid recommendation strategies are inherently more complex than those that use a …

Personalized explanations for hybrid recommender systems

2019

Recommender systems have become pervasive on the web, shaping the way users see information and thus the decisions they make. As these systems get more complex, there is a growing need for transparency. In this …