Instead of behavior cloning, what if you asked an LLM to write code to describe how an agent was acting, and used this to predict their future behavior?
Our new paper "Modeling Others' Minds as Code" shows this outperforms BC by 2x, and reaches human-level performance in predicting human behavior.
My husband presenting his work on caregiving ๐
We analyze the results and find that LLMs learn emergent reasoning patterns like case-by-case analysis and expected value calculation that transfer to improve performance on math questions.
Excited to release our latest paper on a new multi-turn RL objective for training LLMs to *learn how to learn* to adapt to the user. This enables it to adapt and personalize to novel users, whereas the multi-turn RLHF baseline fails to generalize effectively to new users.
RLHF is the main technique for ensuring LLM safety, but it provides no guarantees that they wonโt say something harmful.
Instead, we use online adversarial training to achieve theoretical safety guarantees and substantial empirical safety improvements over RLHF, without sacrificing capabilities.
By optimizing for intrinsic curiosity, the LLM learns how to ask a series of questions over the course of the conversation to improve the accuracy of its user model. This generates conversations which reveal significantly more information about the user.
In our latest paper, we discovered a surprising result: training LLMs with self-play reinforcement learning on zero-sum games (like poker) significantly improves performance on math and reasoning benchmarks, zero-shot. Whaaat? How does this work?
This work shows the benefit of RL training for improving reasoning skills when there is no possibility for data leakage. AND how continuously evolving multi-agent competition leads to the development of emergent skills that generalize to novel tasks.
Natasha Jaques
Just posted a talk I gave about this work! youtu.be/mxWJ9k2XKbk
Natasha Jaques
Natasha Jaques
Natasha Jaques
Natasha Jaques
Natasha Jaques
Natasha Jaques
Natasha Jaques
Natasha Jaques
#HuskyGivingDay is here! Gifts of any amount help unlock up to $10K more for #UWAllen priorities like undergraduate scholarships, which ensures that an Allen School education remains within reach of students regardless of their means. Let's go! bit.ly/hgd-allen-sc... #PoweredByYou #HuskyExperience
