NewXResearch hub
ExploreLibraryProfile
Account
Sign In
Jonathan Herzig
Scholar

Jonathan Herzig

Google Scholar ID: ocQM8FcAAAAJ
Research Scientist, Google
Natural Language ProcessingMachine Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
6,608
 
H-index
29
 
i10-index
40
 
Publications
20
 
Co-authors
0
 
Publications
9 items
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
2026
Cited
0
Latent Reasoning with Supervised Thinking States
2026
Cited
0
HACK: Hallucinations Along Certainty and Knowledge Axes
2025
Cited
0
ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
2025
Cited
0
DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs
2025
Cited
0
Inside-Out: Hidden Factual Knowledge in LLMs
2025
Cited
0
Distinguishing Ignorance from Error in LLM Hallucinations
arXiv.org · 2024
Cited
0
Can Few-shot Work in Long-Context? Recycling the Context to Generate Demonstrations
arXiv.org · 2024
Cited
0