Finding Truth in LLMs: UC Berkeley & Peking U Propose Unsupervised Contrast-Consistent Search | Synced
In the new paper Discovering Latent Knowledge in Language Models Without Supervision, a research team from UC Berkeley and Peking University presents Contrast-Consistent Search (CCS), an unsupervis...
Source: Synced | AI Technology & Industry Review
In the new paper Discovering Latent Knowledge in Language Models Without Supervision, a research team from UC Berkeley and Peking University presents Contrast-Consistent Search (CCS), an unsupervised approach for discovering latent knowledge in language models.