Joschka Braun
@joschkabraun.bsky.social
ML Master's student at University Tübingen | Researching Deep Learning, LLMs, & AI Safety at KASL & Health NLP Lab | https://joschkacbraun.github.io/
1/ Can steering vectors reliably control text properties during summarization?
Our paper "Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization" at the #ICML2025 Workshop on Reliable and Responsible Foundation Models investigates this! 🧵👇
Our paper "Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization" at the #ICML2025 Workshop on Reliable and Responsible Foundation Models investigates this! 🧵👇
July 13, 2025 at 2:36 PM
1/ Can steering vectors reliably control text properties during summarization?
Our paper "Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization" at the #ICML2025 Workshop on Reliable and Responsible Foundation Models investigates this! 🧵👇
Our paper "Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization" at the #ICML2025 Workshop on Reliable and Responsible Foundation Models investigates this! 🧵👇
1/ Controlling LLMs with steering vectors is unreliable, but why? Our paper, "Understanding (Un)Reliability of Steering Vectors in Language Models," at the #ICLR2025 Workshop on
Foundation Models in the Wild investigates this! What did we find?
Foundation Models in the Wild investigates this! What did we find?
May 23, 2025 at 10:04 AM
1/ Controlling LLMs with steering vectors is unreliable, but why? Our paper, "Understanding (Un)Reliability of Steering Vectors in Language Models," at the #ICLR2025 Workshop on
Foundation Models in the Wild investigates this! What did we find?
Foundation Models in the Wild investigates this! What did we find?