Skip to search formSkip to main contentSkip to account menu

Towards a Human-like Open-Domain Chatbot

Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations, is presented and a human evaluation metric called Sensibleness and Specificity Average (SSA) is proposed, which captures key elements of a human-like multi- turn conversation.
arXiv (opens in a new tab)

LaMDA: Language Models for Dialog Applications

It is demonstrated that fine-tuning with annotated data and enabling the model to consult external knowledge sources can lead to significant improvements towards the two key challenges of safety and factual grounding.
arXiv (opens in a new tab)

Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Perfect Reasoners

A novel prompt strategy called Deeply Understanding the Problems (DUP) prompting is proposed, inspired by how humans solve complex reasoning problems, designed to enhance the comprehensive understanding of problems by LLMs.

Question Answering with Dynamic Memory Networks from Knowledge Encoded in Natural Language

This work leverages the works of these authors and explores using Wikipedia articles as a natural language KB using memory network models for question answering over Facebook's bAbI tasks.

Tell me who you are and i’ll tell you what to do: A Persona Grounded task-oriented Dialogue Generation System

This paper proposes a system that is persona-013 specific, can handle chit-chat utterances, and produces responses that add a human element to the conversation, while always remaining grounded on the task.

DG 2 : Data Augmentation Through Document Grounded Dialogue Generation

An automatic data augmentation tech-011 nique grounded on documents through a gen-012 erative dialogue model that achieves significant provement over traditional data augmentation 019 methods in the low-resource setting.

Service Capacity Estimation Through Telemetry Analysis

This work presents a novel method, using machine learning, for estimating actual service capacity, and should help produce a more exact (and therefore cost effective) solution to the problem of capacity planning.

S AFETY B ENCH : Identifying Safety-Sensitive Situations for Open-domain Conversational Systems

This work focuses on the issue of safety for end-to-end conversational AI, and presents S AFETY B ENCH, a set of open-source tooling for quickly assessing safety issues.

How do people talk about images? A study on open-domain conversation on images.

Objects in the image are indeed the most important element for conversations on image, which could be directly discussed or be a bait to other off-image conversations, and enriched the image information with image caption and object tags, increasing the diversity and image-relevancy of generated responses.
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)
  NODES
chat 3
Note 1