Research & reports
Compare studies, open model profiles and trace findings to their source.
2025Read source | Teacher/student LLM pairs across GPT, Qwen, and related shared-initialization settings | Creates + tests | Broader relevance | Behavioral traits can transfer through apparently unrelated filtered data, mainly when teacher and student share initialization. | Training data + behavioral tests | |
|---|---|---|---|---|---|---|
2026Read source | Unverified; no public paper or model list located by the source shelf | Not classified | Broader relevance | The reported claim is that dilution can strengthen compartmentalized backdoors, but the source is forthcoming. | Not specified | No direct match |
Source summaries retain the reported scope. Community claims are author-reported. Portal audit results →