Scholar
Ivaxi Sheth
Google Scholar ID: Isz5M1UAAAAJ
PhD student, CISPA-Helmholtz
Machine Learning
Causality
LLMs
Explainability
Safety
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
136
H-index
6
i10-index
4
Publications
20
Co-authors
14
list available
Publications
18 items
FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy
2026
Cited
0
Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents
2026
Cited
0
Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return
2026
Cited
0
When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM Answering
2026
Cited
0
Mitigating Over-Personalization in LLMs via Structured Memory
2026
Cited
0
Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
2026
Cited
0
Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution
2026
Cited
0
Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition
2026
Cited
0
Load more
Co-authors
12 total
Samira Ebrahimi Kahou
Associate Professor, University of Calgary/Mila/Canada CIFAR AI Chair
Mohammad Havaei
Google
Mario Fritz
Faculty CISPA Helmholtz Center for Information Security; Professor Saarland University
Ruta Binkyte
CISPA Helmholtz Center for Information Security
Sahar Abdelnabi
AI Security Researcher, Microsoft
Mark Gales
Cambridge University
Vyas Raina
University of Cambridge
Stefan Bauer
Helmholtz | TUM | CIFAR
