Paper-Zero-shot.jpg

Controlling language generation models without training data

Giving a neural generation model “control knobs” enables modulation of the content of generated language.

Many popular AI applications — such as machine translation, conversational AI, and question answering — depend on natural-language generation, or producing new sequences of syntactically and semantically coherent text.

Sometimes it’s useful to modulate the output of a language generator: on different occasions, for instance, a machine translation model might need to produce translations that are more formal or more idiomatic; a conversational-AI model might focus more on delivering information or on eliciting responses from a human interlocutor.

Typically, building natural-language-generation (NLG) models that provide this kind of control means re-training them on the appropriate type of annotated data — formal or informal diction, informative or interrogative utterances. But researchers in the Alexa AI organization have invented a method for modulating a language generator’s output without the need for re-training.

Instead, they’ve added what they describe as three “control knobs” to an NLG model, which can vary the model output. They describe their approach in a paper called “Zero-shot controlled generation with encoder-decoder transformers”, which they’ve posted to the arXiv. The paper’s corresponding author, senior applied scientist Mahdi Namazifar, answered 3 questions about his team’s work for Amazon Science.

Q. What does it mean to add a “control knob” to an NLG model?

The general belief in this area is that once you have a trained model, if you go into it and make changes manually, that causes it to degenerate. Contrary to this belief, one of the things that we do in this work is exactly that: we take a trained model and manually manipulate the weights of the model, the parameters of the model. And we show that not only does it not cause degeneration of the model — we see that we can maintain the quality of the generations — but you achieve control by doing this, if you do it in a systematic way and an intuitive way. 

Attention biasing.png
A diagram of the researchers’ attention-biasing “control knob”. The attention distribution learned by a trained model (lower group of blue bars) is re-weighted (bt) and normalized to produce a new distribution.

A good example of that is attention biasing. The attention mechanism makes a decision that at this point I need to pay attention, in this distribution, to the input. We show that we can go into the attention modules and force the trained model to pay more attention to certain parts of the context than it usually would.

For instance, if you have a dialogue model, and we want the next response to the user to be more informative, we can actually force the model to pay more attention to the knowledge snippet that we’ve provided. And again, the expectation would be this would throw off the model completely, but we saw — very surprisingly — that that doesn't happen, and in fact it achieves what we had in mind, and it follows the intuition. 

Q. What are the other two knobs?

Another knob we introduce here is decoder mixing. Imagine you have two different models that have two different decoders, and these decoders have learned different skills. So, for instance, in a conversation and a dialogue system, the decoder has learned, given the dialogue history, how to respond. And imagine a different decoder with a completely different task — for instance, an autoencoder, which, given an encoding of the input, is able to reconstruct the input. So, these two decoders have learned different skills. We show that by mixing them, we can mix the skills that they have learned. This one can respond; this one can copy from the input. If you have, for instance, some knowledge within the input, then combining these allows us to have a response that is more informative. 

The third knob is another interesting one. To get to certain desired controls, what we propose here is to augment the input with certain additional input — which, again, is intuitively designed. For instance, if you want the generated language to be a question, we show that if we get a bunch of questions, and we encode them in a certain way, and we augment our input with this encoding of the questions, the model is able to generate more questions; whatever the model wanted to generate, it generates it in a question manner. Or if you wanted to generate according to a certain topic, you would give it control phrases in that topic, and it would push the model to generate according to that topic, or with a certain sentiment, and so on. 

This is kind of similar to the concept of priming of language models that is out there in the literature, but priming was never shown to work for smaller language models. It was shown to work for language models with hundreds of billions of parameters, which are very computationally expensive to run. But we show that this version of “priming” could allow much, much smaller models — three orders of magnitude smaller models, even — to use this notion of priming in a different way. And again, this knob and the other two need absolutely no additional training and annotated data.

Q. Did you experiment with any other types of control knobs?

Encoder-decoder Transformer-based NLG models have two sets of attentions. One is called self-attention, and one is called cross-attention. Self-attention gets kicked in as the model is generating, and it attends to what it has generated up to this point — “what was the word that came out of my mouth two seconds ago?” Cross-attention pays attention to the context — everything that was said last turn, or some sort of knowledge about the topic of the conversation, and so on. We saw that applying attention biasing on cross-attention worked very well, as is discussed in the paper, but when we apply attention biasing to self-attention, we see basically what we were expecting from the get-go, which was the model starting to generate gibberish, basically, or the models starting to degenerate. 

Control knobs.png
A diagram of the researchers’ model, including the three control knobs that worked (A – C) and one that didn’t (self-attention biasing, D).

After a lot of digging into this, we propose — basically, as a hypothesis — that in these models, this self-attention module is responsible for the fluency of the generated language, and probably that's its main function. So why is this important? We show that if we have another model that is fluent, and we replace this part of the model with another fluent model, we still get good generations. What that tells us is maybe we don't need to focus on training these when we're training a model for whatever task we have. If we have a model that generates fluently, we can just use those weights and modules. 

The benefit of doing that is basically savings in computations. We see that in some cases, we can train the model with 44% fewer weights and parameters and still get pretty competitive numbers, which is very important, because training these models is very expensive. Training time would be reduced significantly, and we can use smaller machines for training the same model, which also reduces the carbon footprint.

That's a secondary kind of contribution of this work, which is focusing on a case where it didn't work. This knob didn't work, and when we dug into why it didn't work, we came to some new findings.

Research areas

Related content

GB, MLN, Edinburgh
We’re looking for a Machine Learning Scientist in the Personalization team for our Edinburgh office experienced in generative AI and large models. You will be responsible for developing and disseminating customer-facing personalized recommendation models. This is a hands-on role with global impact working with a team of world-class engineers and scientists across the Edinburgh offices and wider organization. You will lead the design of machine learning models that scale to very large quantities of data, and serve high-scale low-latency recommendations to all customers worldwide. You will embody scientific rigor, designing and executing experiments to demonstrate the technical efficacy and business value of your methods. You will work alongside a science team to delight customers by aiding in recommendations relevancy, and raise the profile of Amazon as a global leader in machine learning and personalization. Successful candidates will have strong technical ability, focus on customers by applying a customer-first approach, excellent teamwork and communication skills, and a motivation to achieve results in a fast-paced environment. Our position offers exceptional opportunities for every candidate to grow their technical and non-technical skills. If you are selected, you have the opportunity to make a difference to our business by designing and building state of the art machine learning systems on big data, leveraging Amazon’s vast computing resources (AWS), working on exciting and challenging projects, and delivering meaningful results to customers world-wide. Key job responsibilities Develop machine learning algorithms for high-scale recommendations problems. Rapidly design, prototype and test many possible hypotheses in a high-ambiguity environment, making use of both quantitative analysis and business judgement. Collaborate with software engineers to integrate successful experimental results into large-scale, highly complex Amazon production systems capable of handling 100,000s of transactions per second at low latency. Report results in a manner which is both statistically rigorous and compellingly relevant, exemplifying good scientific practice in a business environment.
US, MA, Westborough
Amazon is looking for talented Postdoctoral Scientists to join our Fulfillment Technology and Robotics team for a one-year, full-time research position. The Innovation Lab in BOS27 is a physical space in which new ideas can be explored, hands-on. The Lab provides easier access to tools and equipment our inventors need while also incubating critical technologies necessary for future robotic products. The Lab is intended to not only develop new technologies that can be used in future Fulfillment, Technology, and Robotics products but additionally promote deeper technical collaboration with universities from around the world. The Lab’s research efforts are focused on highly autonomous systems inclusive of robotic manipulation of packages and ASINs, multi-robot systems utilizing vertical space, Amazon integrated gantries, advancements in perception, and collaborative robotics. These five areas of research represent an impactful set of technical capabilities that when realized at a world class level will unlock our desire for a highly automated and adaptable fulfillment supply chain. As a Postdoctoral Scientist you will be developing a coordinated multi-agent system to achieve optimized trajectories under realistic constraints. The project will explore the utility of state-of-the-art methods to solve multi-agent, multi-objective optimization problems with stochastic time and location constraints. The project is motivated by a new technology being developed in the Innovation Lab to introduce efficiencies in the last-mile delivery systems. Key job responsibilities In this role you will: * Work closely with a senior science advisor, collaborate with other scientists and engineers, and be part of Amazon’s diverse global science community. * Publish your innovation in top-tier academic venues and hone your presentation skills. * Be inspired by challenges and opportunities to invent new techniques in your area(s) of expertise.
IN, TS, Hyderabad
Welcome to the Worldwide Returns & ReCommerce team (WWR&R) at Amazon.com. WWR&R is an agile, innovative organization dedicated to ‘making zero happen’ to benefit our customers, our company, and the environment. Our goal is to achieve the three zeroes: zero cost of returns, zero waste, and zero defects. We do this by developing products and driving truly innovative operational excellence to help customers keep what they buy, recover returned and damaged product value, keep thousands of tons of waste from landfills, and create the best customer returns experience in the world. We have an eye to the future – we create long-term value at Amazon by focusing not just on the bottom line, but on the planet. We are building the most sustainable re-use channel we can by driving multiple aspects of the Circular Economy for Amazon – Returns & ReCommerce. Amazon WWR&R is comprised of business, product, operational, program, software engineering and data teams that manage the life of a returned or damaged product from a customer to the warehouse and on to its next best use. Our work is broad and deep: we train machine learning models to automate routing and find signals to optimize re-use; we invent new channels to give products a second life; we develop highly respected product support to help customers love what they buy; we pilot smarter product evaluations; we work from the customer backward to find ways to make the return experience remarkably delightful and easy; and we do it all while scrutinizing our business with laser focus. You will help create everything from customer-facing and vendor-facing websites to the internal software and tools behind the reverse-logistics process. You can develop scalable, high-availability solutions to solve complex and broad business problems. We are a group that has fun at work while driving incredible customer, business, and environmental impact. We are backed by a strong leadership group dedicated to operational excellence that empowers a reasonable work-life balance. As an established, experienced team, we offer the scope and support needed for substantial career growth. Amazon is earth’s most customer-centric company and through WWR&R, the earth is our customer too. Come join us and innovate with the Amazon Worldwide Returns & ReCommerce team!
US, WA, Seattle
Amazon Advertising operates at the intersection of eCommerce and advertising, and is investing heavily in building a world-class advertising business. We are defining and delivering a collection of self-service performance advertising products that drive discovery and sales. Our products are strategically important to our Retail and Marketplace businesses driving long-term growth. We deliver billions of ad impressions and millions of clicks daily and are breaking fresh ground to create world-class products to improve both shopper and advertiser experience. With a broad mandate to experiment and innovate, we grow at an unprecedented rate with a seemingly endless range of new opportunities. The Ad Response Prediction team in Sponsored Products organization build advanced deep-learning models, large-scale machine-learning pipelines, and real-time serving infra to match shoppers’ intent to relevant ads on all devices, for all contexts and in all marketplaces. Through precise estimation of shoppers’ interaction with ads and their long-term value, we aim to drive optimal ads allocation and pricing, and help to deliver a relevant, engaging and delightful ads experience to Amazon shoppers. As the business and the complexity of various new initiatives we take continues to grow, we are looking for talented Applied Scientists to join the team. Key job responsibilities As a Applied Scientist II, you will: * Conduct hands-on data analysis, build large-scale machine-learning models and pipelines * Work closely with software engineers on detailed requirements, technical designs and implementation of end-to-end solutions in production * Run regular A/B experiments, gather data, perform statistical analysis, and communicate the impact to senior management * Establish scalable, efficient, automated processes for large-scale data analysis, machine-learning model development, model validation and serving * Provide technical leadership, research new machine learning approaches to drive continued scientific innovation * Be a member of the Amazon-wide Machine Learning Community, participating in internal and external MeetUps, Hackathons and Conferences
US, WA, Seattle
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video add-on subscriptions such as Apple TV+, Max, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video technologist, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! In Prime Video READI, our mission is to automate infrastructure scaling and operational readiness. We are growing a team specialized in time series modeling, forecasting, and release safety. This team will invent and develop algorithms for forecasting multi-dimensional related time series. The team will develop forecasts on key business dimensions with optimization recommendations related to performance and efficiency opportunities across our global software environment. As a founding member of the core team, you will apply your deep coding, modeling and statistical knowledge to concrete problems that have broad cross-organizational, global, and technology impact. Your work will focus on retrieving, cleansing and preparing large scale datasets, training and evaluating models and deploying them to production where we continuously monitor and evaluate. You will work on large engineering efforts that solve significantly complex problems facing global customers. You will be trusted to operate with complete independence and are often assigned to focus on areas where the business and/or architectural strategy has not yet been defined. You must be equally comfortable digging in to business requirements as you are drilling into design with development teams and developing production ready learning models. You consistently bring strong, data-driven business and technical judgment to decisions. You will work with internal and external stakeholders, cross-functional partners, and end-users around the world at all levels. Our team makes a big impact because nothing is more important to us than delivering for our customers, continually earning their trust, and thinking long term. You are empowered to bring new technologies to your solutions. If you crave a sense of ownership, this is the place to be.
US, WA, Bellevue
mmPROS Surface Research Science seeks an exceptional Applied Scientist with expertise in optimization and machine learning to optimize Amazon's middle mile transportation network, the backbone of its logistics operations. Amazon's middle mile transportation network utilizes a fleet of semi-trucks, trains, and airplanes to transport millions of packages and other freight between warehouses, vendor facilities, and customers, on time and at low cost. The Surface Research Science team delivers innovation, models, algorithms, and other scientific solutions to efficiently plan and operate the middle mile surface (truck and rail) transportation network. The team focuses on large-scale problems in vehicle route planning, capacity procurement, network design, forecasting, and equipment re-balancing. Your role will be to build innovative optimization and machine learning models to improve driver routing and procurement efficiency. Your models will impact business decisions worth billions of dollars and improve the delivery experience for millions of customers. You will operate as part of a team of innovative, experienced scientists working on optimization and machine learning. You will work in close collaboration with partners across product, engineering, business intelligence, and operations. Key job responsibilities - Design and develop optimization and machine learning models to inform our hardest planning decisions. - Implement models and algorithms in Amazon's production software. - Lead and partner with product, engineering, and operations teams to drive modeling and technical design for complex business problems. - Lead complex modeling and data analyses to aid management in making key business decisions and set new policies. - Write documentation for scientific and business audiences. About the team This role is part of mmPROS Surface Research Science. Our mission is to build the most efficient and optimal transportation network on the planet, using our science and technology as our biggest advantage. We leverage technologies in optimization, operations research, and machine learning to grow our businesses and solve Amazon's unique logistical challenges. Scientists in the team work in close collaboration with each other and with partners across product, software engineering, business intelligence, and operations. They regularly interact with software engineering teams and business leadership.
US, CA, Palo Alto
Amazon’s Advertising Technology team builds the technology infrastructure and ad serving systems to manage billions of advertising queries every day. The result is better quality advertising for publishers and more relevant ads for customers. In this organization you’ll experience the benefits of working in a dynamic, entrepreneurial environment, while leveraging the resources of Amazon.com (AMZN), one of the world's leading companies. Amazon Publisher Services (APS) helps publishers of all sizes and on all channels better monetize their content through effective advertising. APS unites publishers with advertisers across devices and media channels. We work with Amazon teams across the globe to solve complex problems for our customers. The end results are Amazon products that let publishers focus on what they do best - publishing. The APS Publisher Products Engineering team is responsible for building cloud-based advertising technology services that help Web, Mobile, Streaming TV broadcasters and Audio publishers grow their business. The engineering team focuses on unlocking our ad tech on the most impactful Desktop, mobile and Connected TV devices in the home, bringing real-time capabilities to this medium for the first time. As a Data Scientist in our team, you will collaborate directly with developers and scientists to produce modeling solutions, you will partner with software developers and data engineers to build end-to-end data pipelines and production code, and you will have exposure to senior leadership as we communicate results and provide scientific guidance to the business. You will analyze large amounts of business data, automate and scale the analysis, and develop metrics (like ROAS, Share of Wallet) that will enable us to continually delight our customers worldwide. As a successful data scientist, you are an analytical problem solver who enjoys diving into data, is excited about investigations and algorithms, can multi-task, and can credibly interface between technical teams and business stakeholders. Your analytical abilities, business understanding, and technical aptitude will be used to identify specific and actionable opportunities to solve existing business problems and look around corners for future opportunities. Your expertise in synthesizing and communicating insights and recommendations to audiences of varying levels of technical sophistication will enable you to answer specific business questions and innovate for the future. Major responsibilities include: · Utilizing code (Apache, Spark, Python, R, Scala, etc.) for analyzing data and building statistical models to solve specific business problems. · Collaborate with product, BIEs, software developers, and business leaders to define product requirements and provide analytical support · Build customer-facing reporting to provide insights and metrics which track system performance · Communicating verbally and in writing to business customers and leadership team with various levels of technical knowledge, educating them about our systems, as well as sharing insights and recommendations
US, CA, El Segundo
Amazon is seeking an exceptional Senior Applied Scientist to join AGI Info Content team. In this role, you will be at the forefront of developing and enhancing the intelligence of AmazonBot crawler and content processing. The team is a key enabler of Amazon's AGI initiatives such as data pipelines for Olympus model training and collecting data for AGI Info grounding services. Our systems operate on web scale. This requires great combination of innovation to utilize all SOTA ML techniques in combination with model optimization to operate on 100k+ requests/decision per second. Your work will directly impact the quality and efficiency of our data acquisition efforts, ultimately benefiting millions of customers worldwide. Key job responsibilities - Design, develop, and implement advanced algorithms and machine learning models to improve the intelligence and effectiveness of our web crawler and content processing pipelines. - Collaborate with cross-functional teams to identify and prioritize crawling targets, ensuring alignment with business objectives - Analyze and optimize crawling strategies to maximize coverage, freshness, and quality of acquired data while minimizing operational costs as well as dive deep into data to select the highest quality data for LLM model training and grounding. - Conduct in-depth research to stay at the forefront of web acquisition and processing. - Develop and maintain scalable, fault-tolerant systems to handle the vast scale of Amazon's web crawling operations - Monitor and analyze performance metrics, identifying opportunities for improvement and implementing data-driven optimizations - Mentor and guide junior team members, fostering a culture of innovation and continuous learning
US, WA, Seattle
Amazon's Pricing & Promotions Optimization Science is seeking a motivated Applied Scientist to harness planet scale multi-modal datasets, and navigate a continuously evolving competitor landscape, in order to regularly generate fresh customer-relevant prices and promotions on billions of Amazon and Third Party Seller products worldwide. We are looking for a talented, organized, and customer-focused applied scientists to define, measure, and launch customer-obsessed solutions across all products listed on Amazon. This role requires an individual with exceptional AI and data science expertise, excellent cross-functional collaboration skills, strong business acumen, and an entrepreneurial spirit. We are looking for an experienced innovator, who is a self-starter, comfortable with ambiguity, demonstrates strong attention to detail, and has the ability to work in a fast-paced and ever-changing environment. Key job responsibilities - See the big picture. Understand and influence the long term vision for Amazon's science-based competitive, perception-preserving pricing/promotion techniques - Build strong collaborations. Partner with product, engineering, and science teams within and outside Pricing & Promotions org to deploy AI/ML solutions at Amazon scale - Stay informed. Establish mechanisms to stay up to date on latest scientific advancements in machine learning, neural networks, natural language processing, probabilistic forecasting, reinforcement learning, and multi-objective optimization techniques. Identify opportunities to apply them to relevant Pricing & Promotions business problems - Keep innovating for our customers. Foster an environment that promotes rapid experimentation, continuous learning, and incremental value delivery - Successfully execute & deliver. Apply your exceptional technical machine learning expertise to incrementally move the needle on some of our hardest science and tech problems About the team About the team: the Pricing and Promotion Optimization team within P2 Science leads the definition, measurement, and implementation of the state-of-the-art AI and data science solutions to improve price/promotion quality across the site and bring value to customers, sellers and Amazon.
US, WA, Bellevue
We are seeking a passionate, talented, and inventive individual to join the Applied AI team and help build industry-leading technologies that customers will love. This team offers a unique opportunity to make a significant impact on the customer experience and contribute to the design, architecture, and implementation of an innovative product. Key job responsibilities On our team you will push the boundaries of ML and Generative AI techniques to scale the inputs for hundreds of billions of dollars of annual revenue for our eCommerce business. If you have a passion for AI technologies, a drive to innovate and a desire to make a meaningful impact, we invite you to become a valued member of our team. We are seeking an experienced Scientist who combines superb technical, research, analytical and leadership capabilities with a demonstrated ability to get the right things done quickly and effectively. This person must be comfortable working with a team of top-notch developers and collaborating with our research teams. We’re looking for someone who innovates, and loves solving hard problems. You will be expected to have an established background in building highly scalable systems and system design, great communication skills, and a motivation to achieve results in a fast-paced environment. You should be somebody who enjoys working on complex problems, is customer-centric, and feels strongly about building good software as well as making that software achieve its operational goals. A day in the life You will be responsible for developing and maintaining the systems and tools that enable us to accelerate knowledge operations and work in the intersection of Science and Engineering. You will push the boundaries of ML and Generative AI techniques to scale the inputs for hundreds of billions of dollars of annual revenue for our eCommerce business. If you have a passion for AI technologies, a drive to innovate and a desire to make a meaningful impact, we invite you to become a valued member of our team. About the team The mission of the Applied AI team is to enable organizations within Worldwide Amazon.com Stores to accelerate the adoption of AI technologies across various parts of our business. We are looking for an Applied Scientist to join our Applied AI team to work on LLM-based solutions.