Sparrow is a chatbot developed by the artificial intelligence research lab

DeepMind DeepMind Technologies is a British artificial intelligence subsidiary of Alphabet Inc. and research laboratory founded in 2010. DeepMind was List of mergers and acquisitions by Google, acquired by Google in 2014 and became a wholly owned subsid ...

, a subsidiary of

Alphabet Inc. Alphabet Inc. is an American multinational technology conglomerate holding company headquartered in Mountain View, California. It was created through a restructuring of Google on October 2, 2015, and became the parent company of Google and sev ...

It is designed to answer users' questions correctly, while reducing the risk of unsafe and inappropriate answers. One motivation behind Sparrow is to address the problem of language models producing incorrect, biased or potentially harmful outputs. Sparrow is trained using human judgements, in order to be more “Helpful, Correct and Harmless” compared to baseline pre-trained language models. 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. To improve accuracy and help avoid the problem of

hallucinating A hallucination is a perception in the absence of an external stimulus that has the qualities of a real perception. Hallucinations are vivid, substantial, and are perceived to be located in external objective space. Hallucination is a combinatio ...

incorrect answers, Sparrow has the ability to search the Internet using Google Search 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. During development study participants were asked to converse with the system and try to trick it into breaking these rules. 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"; however, the bot was not released publicly. DeepMind CEO Demis Hassabis said DeepMind is considering releasing Sparrow for a "private beta" some time in 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 Chinchilla is a family of large language models developed by the research team at DeepMind, presented in March 2022. It is named "chinchilla" because it is a further development over a previous model family named Gopher. Both model families were tr ...

pre-trained

large language model A large language model (LLM) is a language model consisting of a neural network with many parameters (typically billions of weights or more), trained on large quantities of unlabelled text using self-supervised learning. LLMs emerged around 2018 an ...

(LLM), which has 70 Billion parameters. Sparrow is trained using

reinforcement learning from human feedback In machine learning, reinforcement learning from human feedback (RLHF) or reinforcement learning from human preferences is a technique that trains a "reward model" directly from human feedback and uses the model as a reward function to optimize an ...

(RLHF), 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.

Limitations

Sparrow's training data corpus is mainly in English, meaning it performs worse in other languages. When adversarially probed by study participants it breaks the rules 8% of the time; however, this is still three times lower than the baseline prompted pre-trained model (Chinchilla).

References

External links

White paper

Blog post
{{Google AI Chatbots Language modeling Natural language processing Large language models Google DeepMind

Training

Limitations

See also

References

External links