“While this isn't a groundbreaking prompting technique, it does make me wonder if we created a training set that only had high quality text, how different would it be that GPT-4.”
"According to ...": Prompting Language Models Improves Quoting from Pre-Training Data
Large Language Models (LLMs) may hallucinate and generate fake information, despite pre-training on factual data. Inspired by the journalistic device of "according to sources", we propose according-to prompting: directing LLMs to ground responses against previously observed text. To quantify this grounding, we propose a novel evaluation metric (QUIP-Score) that measures the extent to which model-produced answers are directly found in underlying text corpora. We illustrate with experiments on three corpora (Wikipedia, PubMed, and the U.S. legal tax code) that these prompts improve grounding under our metrics, with the additional benefit of often improving end-task performance. Furthermore, prompts that ask the model to decrease grounding (or to ground to other corpora) indeed decrease QUIP-Score, indicating the ability of LLMs to increase or decrease grounded generations on request.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)- “According To..“ Prompting LLMs Improves Quoting from Pre-Training Data ↗tim_sw · 2023-05-30 · 2 分
- “According to” Prompting Language Models Improves Quoting from Pre-Training Data ↗rntn · 2023-08-01 · 2 分