arxiv:2609.10060
Maciej Chrabąszcz
mchraba
AI & ML interests
Representation Engineering, AI Safety, AI Monitoring
Recent Activity
authored a paper about 12 hours ago
Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States submitted a paper about 12 hours ago
Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States authored a paper 4 months ago
Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning DynamicsOrganizations
models 0
None public yet
datasets 0
None public yet