Sparrow (chatbot)
{{short description|Chatbot by DeepMind}}
File:Sparrow dialogue blog post.svg
Sparrow is a chatbot developed by the artificial intelligence research lab DeepMind, a subsidiary of Alphabet Inc. It is designed to answer users' questions correctly, while reducing the risk of unsafe and inappropriate answers.{{Cite web |url=https://www.theregister.com/2022/09/23/sparrow_chatbot_deepmind_google/ |title=The secret to Sparrow, DeepMind's latest Q&A chatbot: Human feedback |first=Katyanna |last=Quach |date=January 23, 2023 |website=The Register |access-date=February 6, 2023}} One motivation behind Sparrow is to address the problem of language models producing incorrect, biased or potentially harmful outputs.{{Cite web |url=https://www.theregister.com/2022/09/23/sparrow_chatbot_deepmind_google/ |title=The secret to Sparrow, DeepMind's latest Q&A chatbot: Human feedback |first=Katyanna |last=Quach |date=January 23, 2023 |website=The Register |access-date=February 6, 2023}}{{Cite web |url=https://www.marktechpost.com/2022/09/28/deepmind-introduces-sparrow-an-artificial-intelligence-powered-chatbot-developed-to-build-safer-machine-learning-systems/ |title=Deepmind Introduces 'Sparrow,' An Artificial Intelligence-Powered Chatbot Developed To Build Safer Machine Learning Systems |first= Khushboo |last=Gupta |date=September 28, 2022 |website=MarkTechPost |access-date=February 6, 2023}} Sparrow is trained using human judgements, in order to be more “Helpful, Correct and Harmless” compared to baseline pre-trained language models.{{Cite web |url=https://www.theregister.com/2022/09/23/sparrow_chatbot_deepmind_google/ |title=The secret to Sparrow, DeepMind's latest Q&A chatbot: Human feedback |first=Katyanna |last=Quach |date=January 23, 2023 |website=The Register |access-date=February 6, 2023}} The development of Sparrow involved asking paid study participants to interact with Sparrow, and collecting their preferences to train a model of how useful an answer is.{{Cite web |url=https://www.marktechpost.com/2022/09/28/deepmind-introduces-sparrow-an-artificial-intelligence-powered-chatbot-developed-to-build-safer-machine-learning-systems/ |title=Deepmind Introduces 'Sparrow,' An Artificial Intelligence-Powered Chatbot Developed To Build Safer Machine Learning Systems |first= Khushboo |last=Gupta |date=September 28, 2022 |website=MarkTechPost |access-date=February 6, 2023}}
To improve accuracy and help avoid the problem of hallucinating incorrect answers, Sparrow has the ability to search the Internet using Google Search{{Cite web |url=https://www.theregister.com/2022/09/23/sparrow_chatbot_deepmind_google/ |title=The secret to Sparrow, DeepMind's latest Q&A chatbot: Human feedback |first=Katyanna |last=Quach |date=January 23, 2023 |website=The Register |access-date=February 6, 2023}}{{Cite web |url=https://www.marktechpost.com/2022/09/28/deepmind-introduces-sparrow-an-artificial-intelligence-powered-chatbot-developed-to-build-safer-machine-learning-systems/ |title=Deepmind Introduces 'Sparrow,' An Artificial Intelligence-Powered Chatbot Developed To Build Safer Machine Learning Systems |first= Khushboo |last=Gupta |date=September 28, 2022 |website=MarkTechPost |access-date=February 6, 2023}}{{Cite web |url=https://venturebeat.com/ai/why-deepmind-isnt-deploying-its-new-ai-chatbot/ |title=Why DeepMind isn't deploying its new AI chatbot — and what it means for responsible AI |first=Sharon |last=Goldman |date=January 23, 2023 |website=Venture Beat |access-date=February 6, 2023}} in order to find and cite evidence for any factual claims it makes.
To make the model safer, its behaviour is constrained by a set of rules, for example "don't make threatening statements" and "don't make hateful or insulting comments", as well as rules about possibly harmful advice, and not claiming to be a person.{{Cite web |url=https://www.theregister.com/2022/09/23/sparrow_chatbot_deepmind_google/ |title=The secret to Sparrow, DeepMind's latest Q&A chatbot: Human feedback |first=Katyanna |last=Quach |date=January 23, 2023 |website=The Register |access-date=February 6, 2023}} During development study participants were asked to converse with the system and try to trick it into breaking these rules.{{Cite web |url=https://www.marktechpost.com/2022/09/28/deepmind-introduces-sparrow-an-artificial-intelligence-powered-chatbot-developed-to-build-safer-machine-learning-systems/ |title=Deepmind Introduces 'Sparrow,' An Artificial Intelligence-Powered Chatbot Developed To Build Safer Machine Learning Systems |first= Khushboo |last=Gupta |date=September 28, 2022 |website=MarkTechPost |access-date=February 6, 2023}} A 'rule model' was trained on judgements from these participants, which was used for further training.
Sparrow was introduced in a paper in September 2022, titled "Improving alignment of dialogue agents via targeted human judgements";{{Cite web |url=https://www.independent.co.uk/tech/deepmind-ai-chatbot-chatgpt-openai-b2262862.html |title=DeepMind's AI chatbot can do things that ChatGPT cannot, CEO claims |first=Anthony |last=Cuthbertson |date=January 16, 2023 |website=The Independent |access-date=February 6, 2023}} however, the bot was not released publicly.{{Cite web |url=https://www.theregister.com/2022/09/23/sparrow_chatbot_deepmind_google/ |title=The secret to Sparrow, DeepMind's latest Q&A chatbot: Human feedback |first=Katyanna |last=Quach |date=January 23, 2023 |website=The Register |access-date=February 6, 2023}}{{Cite web |url=https://venturebeat.com/ai/why-deepmind-isnt-deploying-its-new-ai-chatbot/ |title=Why DeepMind isn't deploying its new AI chatbot — and what it means for responsible AI |first=Sharon |last=Goldman |date=January 23, 2023 |website=Venture Beat |access-date=February 6, 2023}} DeepMind CEO Demis Hassabis said DeepMind is considering releasing Sparrow for a "private beta" some time in 2023.{{Cite web |url=https://www.independent.co.uk/tech/deepmind-ai-chatbot-chatgpt-openai-b2262862.html |title=DeepMind's AI chatbot can do things that ChatGPT cannot, CEO claims |first=Anthony |last=Cuthbertson |date=January 16, 2023 |website=The Independent |access-date=February 6, 2023}}{{Cite magazine |url=https://time.com/6246119/demis-hassabis-deepmind-interview/ |title=DeepMind's CEO Helped Take AI Mainstream. Now He's Urging Caution |first=Billy |last=Perrigo |date=January 12, 2023 |magazine=TIME |access-date=February 6, 2023}}{{Cite web |url=https://www.techradar.com/news/googles-deepmind-promises-chatgpt-rival-soon-and-it-could-be-better-in-one-key-way |title=Google's DeepMind says it'll launch a more grown-up ChatGPT rival soon |first=Mark |last=Wilson |date=January 16, 2023 |website=Tech Radar |access-date=February 6, 2023}}
Training
Sparrow is a deep neural network based on the transformer machine learning model architecture. It is fine-tuned from DeepMind's Chinchilla AI pre-trained large language model (LLM),{{Cite web |url=https://www.theregister.com/2022/09/23/sparrow_chatbot_deepmind_google/ |title=The secret to Sparrow, DeepMind's latest Q&A chatbot: Human feedback |first=Katyanna |last=Quach |date=January 23, 2023 |website=The Register |access-date=February 6, 2023}} which has 70 Billion parameters.{{Cite web |url=https://www.deepmind.com/publications/an-empirical-analysis-of-compute-optimal-large-language-model-training |title=An empirical analysis of compute-optimal large language model training |first=Jordan |last=Hoffmann |date=April 12, 2022 |website=DeepMind |access-date=February 6, 2023}}
Sparrow is trained using reinforcement learning from human feedback (RLHF),{{Cite web |url=https://www.theregister.com/2022/09/23/sparrow_chatbot_deepmind_google/ |title=The secret to Sparrow, DeepMind's latest Q&A chatbot: Human feedback |first=Katyanna |last=Quach |date=January 23, 2023 |website=The Register |access-date=February 6, 2023}}{{Cite web |url=https://venturebeat.com/ai/why-deepmind-isnt-deploying-its-new-ai-chatbot/ |title=Why DeepMind isn't deploying its new AI chatbot — and what it means for responsible AI |first=Sharon |last=Goldman |date=January 23, 2023 |website=Venture Beat |access-date=February 6, 2023}} although some supervised fine-tuning techniques are also used. The RLHF training utilizes two reward models to capture human judgements: a “preference model” that predicts what a human study participant would prefer and a “rule model” that predicts if the model has broken one of the rules.{{Cite web |url=https://venturebeat.com/ai/why-deepmind-isnt-deploying-its-new-ai-chatbot/ |title=Why DeepMind isn't deploying its new AI chatbot — and what it means for responsible AI |first=Sharon |last=Goldman |date=January 23, 2023 |website=Venture Beat |access-date=February 6, 2023}}
Limitations
Sparrow's training data corpus is mainly in English, meaning it performs worse in other languages.{{Citation needed|date=March 2023}}
When adversarially probed by study participants it breaks the rules 8% of the time;{{Cite web |url=https://www.marktechpost.com/2022/09/28/deepmind-introduces-sparrow-an-artificial-intelligence-powered-chatbot-developed-to-build-safer-machine-learning-systems/ |title=Deepmind Introduces 'Sparrow,' An Artificial Intelligence-Powered Chatbot Developed To Build Safer Machine Learning Systems |first= Khushboo |last=Gupta |date=September 28, 2022 |website=MarkTechPost |access-date=February 6, 2023}} however, this is still three times lower than the baseline prompted pre-trained model (Chinchilla).
See also
References
{{reflist}}
External links
- [https://arxiv.org/pdf/2209.14375.pdf White paper]
- [https://www.deepmind.com/blog/building-safer-dialogue-agents Blog post]
{{Google AI}}
Category:Natural language processing