BiDPO

Creator

Creator

Seonglae Cho

Created

Created

2025 Feb 1 17:26

Editor

Editor

Seonglae Cho

Edited

Edited

2025 Aug 10 21:49

Refs

Refs

Not contrastive prompts like

CAA, use

Preference Optimization technique such as DPO

Personalized Steering of Large Language Models: Versatile Steering...

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct...

https://openreview.net/forum?id=7qJFkuZdYo

https://arxiv.org/pdf/2406.00045

gemini

Steering Gemini with BiDPO — LessWrong

We tried boosting Gemini benchmarks by optimizing steering vectors. It didn't work. We share our takeaways.

Steering Gemini with BiDPO — LessWrong

https://www.lesswrong.com/posts/WqjkqrEyFDXoHzz9K/steering-gemini-with-bidpo

Steering Gemini with BiDPO — LessWrong

Steering Gemini Using BIDPO Vectors

We tried boosting Gemini benchmarks by optimizing steering vectors. It didn't work. We share our takeaways.

Steering Gemini Using BIDPO Vectors

https://turntrout.com/gemini-steering

Steering Gemini Using BIDPO Vectors

Recommendations

///////////