Internet-Augmented Dialogue Generation

by   Mojtaba Komeili, et al.

The largest store of continually updating knowledge on our planet can be accessed via internet search. In this work we study giving access to this information to conversational agents. Large language models, even though they store an impressive amount of knowledge within their weights, are known to hallucinate facts when generating dialogue (Shuster et al., 2021); moreover, those facts are frozen in time at the point of model training. In contrast, we propose an approach that learns to generate an internet search query based on the context, and then conditions on the search results to finally generate a response, a method that can employ up-to-the-minute relevant information. We train and evaluate such models on a newly collected dataset of human-human conversations whereby one of the speakers is given access to internet search during knowledgedriven discussions in order to ground their responses. We find that search-query based access of the internet in conversation provides superior performance compared to existing approaches that either use no augmentation or FAISS-based retrieval (Lewis et al., 2020).


page 1

page 10

page 11

page 16

page 17

page 18


Language Models that Seek for Knowledge: Modular Search Generation for Dialogue and Prompt Completion

Language models (LMs) have recently been shown to generate more factual ...

DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks

Recent advances in neural sequence-to-sequence models have led to promis...

Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback

Frozen models trained to mimic static datasets can never improve their p...

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

We present BlenderBot 3, a 175B parameter dialogue model capable of open...

The Adapter-Bot: All-In-One Controllable Conversational Model

Considerable progress has been made towards conversational models that g...

Supporting search engines with knowledge and context

Search engines leverage knowledge to improve information access. In orde...

An Ensemble Dialogue System for Facts-Based Sentence Generation

This study aims to generate responses based on real-world facts by condi...

Code Repositories


🌞 Profile of 𝘼𝙡𝙚𝙭𝙖𝙣𝙙𝙚𝙧 𝙍𝙤𝙜𝙖𝙡𝙨𝙠𝙞𝙮

view repo