Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
arxiv(2024)
摘要
Language models are aligned to emulate the collective voice of many,
resulting in outputs that align with no one in particular. Steering LLMs away
from generic output is possible through supervised finetuning or RLHF, but
requires prohibitively large datasets for new ad-hoc tasks. We argue that it is
instead possible to align an LLM to a specific setting by leveraging a very
small number (<10) of demonstrations as feedback. Our method, Demonstration
ITerated Task Optimization (DITTO), directly aligns language model outputs to a
user's demonstrated behaviors. Derived using ideas from online imitation
learning, DITTO cheaply generates online comparison data by treating users'
demonstrations as preferred over output from the LLM and its intermediate
checkpoints. We evaluate DITTO's ability to learn fine-grained style and task
alignment across domains such as news articles, emails, and blog posts.
Additionally, we conduct a user study soliciting a range of demonstrations from
participants (N=16). Across our benchmarks and user study, we find that
win-rates for DITTO outperform few-shot prompting, supervised fine-tuning, and
other self-play methods by an average of 19
feedback directly, DITTO offers a novel method for effective customization of
LLMs.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要