Persona Cartography: Charting Language Model Personality Traits in Weight Space

·LessWrong··

This post summarises the paper Persona Cartography: Charting Language Model Personality Traits in Weight Space.Paper | GitHub | HuggingFaceTL;DRUnderstanding and controlling the character of LLMs is important for safety, as we want our models to be good by disposition.We use a modified Open Character Training pipeline for instilling Big-5 OCEAN personality traits in LLMs across a range of families and sizes (Llama 3.1/Qwen3/Gemma3 sizes 4B-32B).We show that we can scale, invert and combine these...

Read full article →

Related Articles

Xiaomi: New CPU matches Apple cores single threaded, much faster multithreaded
tosh · Hacker News · 8h ago
MS Paint and Photos inivisibly watermark even locally generated output with GUID
ComputerGuru · Hacker News · 8h ago
IPFS Maintainers Winding Down
iand · Hacker News · 7h ago
LLMs could control their host machines by exploiting inference engines
zdw · Hacker News · 4h ago
FDA clears blood test to aid evaluation for Alzheimer's disease
dabinat · Hacker News · 17h ago