method · first seen 12 Oct 2026
synthetic document finetuning
Fine-tuning language models on generated documents to instill beliefs or behavioral tendencies.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Social Priors: Descriptions of AI Users Shape How Language Models Trust and CooperatePapers · 12 Oct 2026 · Harsh Kumar, George Eilender, Ashton Anderson
- Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document FinetuningPapers · 23 Oct 2026 · Ardy Haroen, Florian Lorkowski, Samuel Nellessen, Felix Hofstätter
Latest sources
- Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document FinetuningPapers · 23 Oct 2026 · Ardy Haroen, Florian Lorkowski, Samuel Nellessen, Felix Hofstätter
- Social Priors: Descriptions of AI Users Shape How Language Models Trust and CooperatePapers · 12 Oct 2026 · Harsh Kumar, George Eilender, Ashton Anderson