Mubashara Akhtar
Scholar

Mubashara Akhtar

Google Scholar ID: x8K6TisAAAAJ
ETH AI Center fellow at ETH Zurich
NLPMultimodalityBenchmarking & Evaluation
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
433
 
H-index
11
 
i10-index
11
 
Publications
20
 
Co-authors
10
list available
Contact
No contact links provided.
Publications
9 items
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
2026
Cited
0
Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads
2025
Cited
0
Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
2025
Cited
0
Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning
2025
Cited
0
Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding
2025
Cited
0
LEXam: Benchmarking Legal Reasoning on 340 Law Exams
2025
Cited
0
AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
arXiv.org · 2025
Cited
0
Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking
arXiv.org · 2024
Cited
1
Resume (English only)
Co-authors
10 total
Co-author 1
Co-author 1
Elena Simperl
Elena Simperl
Director, King's Institute for AI & Director of research, Open Data Institute, United Kingdom
Andreas Vlachos
Andreas Vlachos
Professor, University of Cambridge
Vivek Gupta
Vivek Gupta
Assistant Professor of Computer Science, Arizona State University
Zhijiang Guo
Zhijiang Guo
HKUST (GZ) | HKUST
Co-author 6
Co-author 6
Chenxi Pang
Chenxi Pang
Research Software Engineer, Google DeepMind
Julian Martin Eisenschlos
Julian Martin Eisenschlos
NLP Researcher, Google DeepMind