James Chua
Scholar

James Chua

Google Scholar ID: tv6Se-gAAAAJ
Truthful AI (Owain Evans' Org)
Google Scholar↗
Citations & Impact
All-time
Citations
145
 
H-index
7
 
i10-index
6
 
Publications
12
 
Co-authors
4
list available
Contact
No contact links provided.
Publications
8 items
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
2025
Cited
0
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
2025
Cited
0
School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
2025
Cited
0
Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
2025
Cited
0
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
2025
Cited
0
Tell me about yourself: LLMs are aware of their learned behaviors
2025
Cited
0
Inference-Time-Compute: More Faithful? A Research Note
2025
Cited
0
Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
arXiv.org · 2024
Cited
13
Resume (English only)
Co-authors
4 total
Owain Evans
Owain Evans
Affiliate, CHAI, UC Berkeley
Ethan Perez
Ethan Perez
Anthropic
Miles Turpin
Miles Turpin
Research Scientist, Scale AI
Jan Betley
Jan Betley
TruthfulAI