We’ve always had a soft spot for language at Google. Early on, we set out to translate the web. More recently, we’ve invented machine learning techniques that help us better grasp the intent of Search queries. Over time, our advances in these and other areas have made it easier and easier to organize and access the heaps of information conveyed by the written and spoken word.
But there’s always room for improvement. Language is remarkably nuanced and adaptable. It can be literal or figurative, flowery or plain, inventive or informational. That versatility makes language one of humanity’s greatest tools — and one of computer science’s most difficult puzzles.
LaMDA, our latest research breakthrough, adds pieces to one of the most tantalizing sections of that puzzle: conversation.
While conversations tend to revolve around specific topics, their open-ended nature means they can start in one place and end up somewhere completely different. A chat with a friend about a TV show could evolve into a discussion about the country where the show was filmed before settling on a debate about that country’s best regional cuisine.
That meandering quality can quickly stump modern conversational agents (commonly known as chatbots), which tend to follow narrow, pre-defined paths. But LaMDA — short for “Language Model for Dialogue Applications” — can engage in a free-flowing way about a seemingly endless number of topics, an ability we think could unlock more natural ways of interacting with technology and entirely new categories of helpful applications.
The long road to LaMDA
LaMDA’s conversational skills have been years in the making. Like many recent language models, including BERT and GPT-3, it’s built on Transformer, a neural network architecture that Google Research invented and open-sourced in 2017. That architecture produces a model that can be trained to read many words (a sentence or paragraph, for example), pay attention to how those words relate to one another and then predict what words it thinks will come next.
But unlike most other language models, LaMDA was trained on dialogue. During its training, it picked up on several of the nuances that distinguish open-ended conversation from other forms of language. One of those nuances is sensibleness. Basically: Does the response to a given conversational context make sense? For instance, if someone says:
“I just started taking guitar lessons.”
You might expect another person to respond with something like:
“How exciting! My mom has a vintage Martin that she loves to play.”
That response makes sense, given the initial statement. But sensibleness isn’t the only thing that makes a good response. After all, the phrase “that’s nice” is a sensible response to nearly any statement, much in the way “I don’t know” is a sensible response to most questions. Satisfying responses also tend to be specific, by relating clearly to the context of the conversation. In the example above, the response is sensible and specific.
LaMDA builds on earlier Google research, published in 2020, that showed Transformer-based language models trained on dialogue could learn to talk about virtually anything. Since then, we’ve also found that, once trained, LaMDA can be fine-tuned to significantly improve the sensibleness and specificity of its responses.
Responsibility first
These early results are encouraging, and we look forward to sharing more soon, but sensibleness and specificity aren’t the only qualities we’re looking for in models like LaMDA. We’re also exploring dimensions like “interestingness,” by assessing whether responses are insightful, unexpected or witty. Being Google, we also care a lot about factuality (that is, whether LaMDA sticks to facts, something language models often struggle with), and are investigating ways to ensure LaMDA’s responses aren’t just compelling but correct.
But the most important question we ask ourselves when it comes to our technologies is whether they adhere to our AI Principles. Language might be one of humanity’s greatest tools, but like all tools it can be misused. Models trained on language can propagate that misuse — for instance, by internalizing biases, mirroring hateful speech, or replicating misleading information. And even when the language it’s trained on is carefully vetted, the model itself can still be put to ill use.
Our highest priority, when creating technologies like LaMDA, is working to ensure we minimize such risks. We’re deeply familiar with issues involved with machine learning models, such as unfair bias, as we’ve been researching and developing these technologies for many years. That’s why we build and open-source resources that researchers can use to analyze models and the data on which they’re trained; why we’ve scrutinized LaMDA at every step of its development; and why we’ll continue to do so as we work to incorporate conversational abilities into more of our products.
