Till Saenger retweetledi
Pre-filling is the driving force behind STATe-of-Thouguts, (arxiv.org/abs/2602.14265), my new paper with @trsaenger , @GiladMorad12 , @ofraam , @b_m_stewart , and @amir_feder .
How is it useful beyond its typical application to Red-Teaming LLMs?
🧵👇
#NLProc #reasoning
Zachary Bamberger@ZacharyBamberg1
Tree-of-Thoughts & Best-of-N use high-temperature sampling to elicit diverse responses, but they're often very similar. STATe-of-Thoughts replaces high-temperature sampling with "branching" through pre-filled textual interventions 🔼Diversity 🔼Control 🔼Interpretability 1/11🧵👇
English
