SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.08745 · ACL Findings · 2022

Multi-Stage Prompting for Knowledgeable Dialogue Generation

Bryan Catanzaro, Wei Ping, Mohammad Shoeybi, Mostofa Patwary, Shrimai Prabhumoye, Ryan Prenger, Zihan Liu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Existing knowledge-grounded dialogue systems typically use finetuned versions of a pretrained language model (LM) and large-scale knowledge bases. These models typically fail to generalize on topics outside of the knowledge base, and require maintaining separate potentially large checkpoints each time finetuning is needed. In this paper, we aim to address these limitations by leveraging the inherent knowledge stored in the pretrained LM as well as its powerful generation ability. We propose a multi-stage prompting approach to generate knowledgeable responses from a single pretrained LM. We first prompt the LM to generate knowledge based on the dialogue context. Then, we further prompt it to generate responses based on the dialogue context and the previously generated knowledge. Results show that our knowledge generator outperforms the state-of-the-art retrieval-based model by 5.8% when combining knowledge relevance and correctness. In addition, our multi-stage prompting outperforms the finetuning-based dialogue model in terms of response knowledgeability and engagement by up to 10% and 5%, respectively. Furthermore, we scale our model up to 530 billion parameters and show that larger LMs improve the generation correctness score by up to 10%, and response relevance, knowledgeability and engagement by up to 10%. Our code is available at: https:// github.com/NVIDIA/Megatron-LM.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.08745")
get_code_for_paper("2203.08745")
have("2203.08745")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.08745.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.08745.svg)](https://syntology.ai/paper/2203.08745)

Connect an agent — have() is free.