Researcher — paper.dinq.me

2026 顶会论文

一作ACL 2026Poster· Natural Language Processing

What About the Scene With the H itler Reference? HAUNT : A Framework to Probe LLM s’ Self-consistency in Closed Domains Via Adversarial Nudge

Arka Dutta · Sujan Dutta · Rijul Magu · Soumyajit Datta · Munmun De Choudhury · Ashiqur R. KhudaBukhsh

摘要

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 testing factual fidelity in LLMs in the presence of adversarial nudge. Our framework consists of three steps. First, we in...

安全可解释性评测与基准OpenReview 项目页

一作ACL 2026Findings· Findings of ACL

Auditing LLM Responses to Harmful Stereotypes Targeting Mental Health Groups

Arka Dutta · Rijul Magu · Sean Kim · Seohee Yoon · Munmun De Choudhury · Ashiqur R. KhudaBukhsh

摘要

Large Language Models (LLMs) can exhibit imbalanced biases against vulnerable groups, but how they rationalize stereotypes and rights restrictions targeting mental health entities remains underexplored. We audit a broad suite of open-weight LLMs on stereotype-justification prompts tied to mental...

安全社会与人本评测与基准OpenReview 项目页

一作AAAI 2026Poster· Artificial Intelligence

How Can You Tell if Your Large Language Model Could Be a Closet Antisemite? An Explainability-Based Audit Framework for Implicit Bias

Arka Dutta · Reza Fayyazi · Shanchieh Yang · Ashiqur R. KhudaBukhsh

社会与人本OpenReview

Arka Dutta

获取完整研究档案

联系方式

2026 顶会论文

What About the Scene With the H itler Reference? HAUNT : A Framework to Probe LLM s’ Self-consistency in Closed Domains Via Adversarial Nudge

Auditing LLM Responses to Harmful Stereotypes Targeting Mental Health Groups

How Can You Tell if Your Large Language Model Could Be a Closet Antisemite? An Explainability-Based Audit Framework for Implicit Bias

常见合作者