most citedWhat About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.CLShow all

3 papers · 1 filter

cs.CL2025★ 1 cited

What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge

Arka Dutta, Sujan Dutta, Rijul Magu +3

Hallucinations pose a critical challenge to the real-world deployment of large language models (LLMs) in high-stakes domains. In this paper, we present a framework for stress testi…

cs.CL2025

Navigating the Rabbit Hole: Emergent Biases in LLM-Generated Attack Narratives Targeting Mental Health Groups

Rijul Magu, Arka Dutta, Sean Kim +2

Large Language Models (LLMs) have been shown to demonstrate imbalanced biases against certain groups. However, the study of unprovoked targeted attacks by LLMs towards at-risk popu…

cs.CL2023

Down the Toxicity Rabbit Hole: A Novel Framework to Bias Audit Large Language Models

Arka Dutta, Adel Khorramrouz, Sujan Dutta +1

This paper makes three contributions. First, it presents a generalizable, novel framework dubbed \textit{toxicity rabbit hole} that iteratively elicits toxic content from a wide su…