“According to . . . ”: Prompting Language Models Improves Quoting from Pre-Training Data
By Orion Weller, Marc Marone, Nathaniel Weir, Dawn J Lawrie, Daniel Khashabi, Benjamin Van Durme. 2023
63 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Large Language Models, Prompting & Reasoning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mark Yatskar
- Mohit Bansal
- Dan Roth
- Sihao Chen
- Chaitanya Malaviya
- Elizabeth Sieber
- Subin Lee
- Yejin Choi
In Large Language Models
In Prompting & Reasoning
Citations in the corpus
- ExpertQA: Expert-Curated Questions and Attributed Answers (2023, background): “The first class of systems is vanilla LLM prompting (Tay et al., 2022; Weller et al., 2023), where LLMs such as GPT-4 (OpenAI, 2023) are prompted to return attributions (in the form of titles of references, optionally accompanied with URLs) along with their answers.”