SA
Sandeep Atluri
cs.CLcs.AIcs.LGcs.CYcs.CRcs.IRcs.MA
On Valency
published · living versionsW_5tfddhs5·v1 · currentpublished
ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender
with Qiyao Ma, Xiaodong Liu, Weiwei Yang, Mingqian Feng +7
1 version
Preprints & journals
8 papers in the corpus · 2021–2026ASSERT: A Measurement Pipeline for GenAI Audits2608.13840v1 · Riccardo Fogliato, Abhinav Palia, Xiawei Wang et al.2026 · 0 citationsarXiv
Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting2607.26200v1 · Mengya Hu, Susie Park, Suzana Ilic et al.2026 · 0 citationsarXiv
From Prompt Risk to Response Risk: Paired Analysis of Safety Behavior of Large Language Models2604.26052v4 · Mengya Hu, Qiong Wei, Sandeep Atluri2026 · 0 citationsarXiv
AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models2604.22871v1 · Tanmay Gautam, Alireza Bahramali, Sandeep Atluri2026 · 0 citationsarXiv
The Amazon Nova Family of Models: Technical Report and Model Card2506.12103v1 · Amazon AGI, Aaron Langford, Aayush Shah et al.2025 · 2 citationsarXiv
PLAtE: A Large-scale Dataset for List Page Web Extraction2205.12386v2 · Aidan San, Yuan Zhuang, Jan Bakus et al.2022 · 0 citationsarXiv
Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning2109.04689v1 · Li Zhou, Kevin Small, Yong Zhang et al.2021 · 2 citationsarXiv
Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization2108.02859v2 · Markus Dreyer, Mengwen Liu, Feng Nan et al.2021 · 8 citationsarXiv
Career total: 12 works. 8 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.