Chatbot
169 papers with code • 0 benchmarks • 8 datasets
Chatbot or conversational AI is a language model designed and implemented to have conversations with humans.
Source: Open Data Chatbot
Benchmarks
These leaderboards are used to track progress in Chatbot
Libraries
Use these libraries to find Chatbot models and implementationsDatasets
Blended Skill Talk
Taiga Corpus
Most implemented papers
End-to-End Task-Completion Neural Dialogue Systems
One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges.
QLoRA: Efficient Finetuning of Quantized LLMs
artidoro/qlora
•
•
NeurIPS 2023
Our best model family, which we name Guanaco, outperforms all previous openly released models on the Vicuna benchmark, reaching 99. 3% of the performance level of ChatGPT while only requiring 24 hours of finetuning on a single GPU.
Visual Dialog
We introduce the task of Visual Dialog, which requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content.
Deep Reinforcement Learning for Dialogue Generation
liuyuemaicha/Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow
•
•
EMNLP 2016
Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes.
Recipes for building an open-domain chatbot
facebookresearch/ParlAI
•
•
EACL 2021
Building open-domain chatbots is a challenging area for machine learning research.
Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data
project-baize/baize-chatbot
•
•
Furthermore, we propose a new technique called Self-Distill with Feedback, to further improve the performance of the Baize models with feedback from ChatGPT.
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
lm-sys/fastchat
•
•
NeurIPS 2023
Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences.
Mistral 7B
We introduce Mistral 7B v0. 1, a 7-billion-parameter language model engineered for superior performance and efficiency.
Subword Semantic Hashing for Intent Classification on Small Datasets
In this paper, we introduce the use of Semantic Hashing as embedding for the task of Intent Classification and achieve state-of-the-art performance on three frequently used benchmarks.
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
PaddlePaddle/Knover
•
•
Findings (ACL) 2021
To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning.
