SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.01587 · EMNLP · 2022

Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation

Liwei Wang, Michael Lyu, Yanyang Li, Jianqiao Zhao

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

Recent advances in large-scale pre-training provide large models with the potential to learn knowledge from the raw text. It is thus natural to ask whether it is possible to leverage these large models as knowledge bases for downstream tasks. In this work, we answer the aforementioned question in unsupervised knowledge-grounded conversation. We explore various methods that best elicit knowledge from large models. Our human study indicates that, though hallucinations exist, large models post the unique advantage of being able to output common sense and summarize facts that cannot be directly retrieved from the search engine. To better exploit such generated knowledge in dialogue generation, we treat the generated knowledge as a noisy knowledge source and propose the posterior-based reweighing as well as the noisy training strategy. Empirical results on two benchmarks show advantages over the state-of-the-art methods.

For agents

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

get_harvested_code_for_paper("2211.01587")
get_code_for_paper("2211.01587")
have("2211.01587")

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

curl https://syntology.ai/api/ran/2211.01587.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.01587.svg)](https://syntology.ai/paper/2211.01587)

Connect an agent — have() is free.