Updating large language models by directly editing network layers

Automated method that uses gradients to identify salient layers prevents regression on previously seen data.

One of the great attractions of large language models (LLMs) is that they encode information about the real world. But the world is constantly changing, and an LLM’s information is only as fresh as the data it was trained on.

Training an LLM can take months, even when the task is parallelized across 1,000 servers, so AI researchers have sought alternate ways to update LLMs’ knowledge. One of these is to directly edit targeted layers of an LLM, to improve its performance on a particular knowledge-based task. This is a task-specific solution, not a general solution, but it takes hours to implement rather than months.

Related content
Using gradient diversity to optimize selection of past samples for retention improves performance while combatting catastrophic forgetting.

Existing techniques for direct layer editing generally require either manual selection of layers to be edited or a time-consuming procedure to determine the layers where editing will do the most good. Last week, at the 2024 meeting of the European Chapter of the Association for Computational Linguistics, we presented a new method for automatically selecting layers to be edited, which yields more-accurate updates than previous automated methods.

Compared to the prior method for manual layer selection, it also limits regression, or post-update backsliding on data that the model previously handled correctly. On some datasets, our method, which we call SaLEM (for salient-layers editing model), reduced regression by an order of magnitude, while offering equivalent accuracy on new data.

Identifying layers

We consider the case in which an LLM has been fine-tuned on a specific task, such as determining whether one input sentence logically entails or counts as evidence for or against another. In such cases, the model input is typically a pair of texts, and the output is a decision such as “entailed” or “supported”.

Related content
New approach enables sustainable machine learning for remote-sensing applications.

In the prior approach to manual layer selection, known as causal tracing, the first token of each training example is fed to the model, then the first and second, then the first, second, and third, and so on. Then the process is repeated with one of the model layers masked. This two-step analysis, in turn, must be repeated for each layer of the network, a time-consuming procedure.

In our case, we instead prepare an “edit dataset”, consisting of input-output pairs drawn from three groups: (1) the pass samples, for which the existing model outputs the correct answers; (2) the fail samples, for which the existing model outputs the wrong answers; and (3) the adapt samples, which are semantically equivalent to the fail samples but differently phrased.

For each sample, we compute the loss between the existing model’s output and the target output and the corresponding gradients — the modifications of model weights that make correct outputs more likely. Then we average the gradients across each layer of the model and across all training samples. The layer with highest average gradient — the layer that requires the largest modification to accommodate new facts about the world — is the one we edit.

At left is a neural network, labeled "pre-edit model", each of whose input nodes receives a single token from the string "<CLS> The high minded dismissal [SEP] A dismissal of a higher mind". The output of the model is the prediction "Contradict". Encodings from the network pass to a block labeled "SaLEM", in which gradients for each input token are calculated and the most-salient layer identified. The outputs of the block are edits to the layer weights. At right is another version of the neural network at left, labeled "post-edit model". Here, the output is "Entailed" rather than "Contradict".
An example of SaLEM in action. The inputs to the model are the two phrases "The high-minded dismissal" and "A dismissal of a higher mind". Before layer editing, the model incorrectly labels the phrases as contradictory; after layer editing, it correctly labels their relationship as one of entailment.

Layer editing

To edit the selected layer, we use the MEND method proposed by Stanford University researchers in 2022. With MEND, a second machine learning model, the editor model, is trained to, essentially, take gradients as inputs and output parameter edits.

But rather than the raw gradients, the model’s inputs are a low-rank approximation of the gradients, which reduces the dimension of the data by identifying the axes along which most of the variance occurs. This is something like teasing out the underlying causes of the larger gradients, which helps the model generalize better. We also guard against overfitting by aggregating gradients in batches of 10 before computing their low-rank approximation.

Related content
EMNLP papers examine constrained generation of rewrite candidates and automatic selection of information-rich training data.

We use two training objectives to train the editor, one that maximizes the likelihood of correct answers on inputs from the fail and adapt sets and one that minimizes output divergence on inputs from the pass set. This helps prevent regression.

In the original MEND paper, the Stanford researchers used this approach to edit the top three layers of a fine-tuned LLM, a reasonable heuristic for trading off editing efficiency, correction of outputs, and prevention of regression. Because SaLEM identifies the one layer most implicated in the new model update, it can match MEND’s performance on new data. But because it modifies parameters in one layer rather than three, it reduces regression.

Experiments

We evaluated SaLEM on six datasets used to fine-tune LLMs on natural-language-processing tasks. Four of the datasets had to do with natural-language inference, one was a question-answering dataset, and one was a dataset for the standard LLM task of next-token prediction. For the question-answering and generation tasks, we compared SaLEM and the baselines on four different LLM architectures. We measured performance using both edit accuracy, or post-editing accuracy on the new data, and drawdown, which measures regression on the old data.

Related content
Using lists of rare or out-of-vocabulary words to bias connectionist temporal classification models enables personalization.

On the inference tasks, SaLEM matched the edit accuracy of the top performers but had significantly better drawdown — four and ten times better than the second-best performer on two of the datasets. On the other two tasks, SaLEM finished second on both measures to an approach called editable neural networks (ENN). But ENN requires two copies of an LLM to run simultaneously, which is resource intensive. Indeed, for two of the four LLM architectures we tested, we were unable to run ENN because of its computational demands.

In ongoing work, we are investigating (1) enriching the editing dataset with better failed samples and their semantic and counterfactual equivalents, (2) a better weight update mechanism to inform the editor about the extent of updates for borderline instances, and (3) a method of performing edits without loading the full model into memory, as we currently do.

Related content

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!
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, 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, 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 team member, 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! Key job responsibilities As an Applied Scientist in the Content Understanding Team, you will lead the end-to-end research and deployment of video and multi-modal models applied to a variety of downstream applications. More specifically, you will: - Work backwards from customer problems to research and design scientific approaches for solving them - Work closely with other scientists, engineers and product managers to expand the depth of our product insights with data, create a variety of experiments to determine the high impact projects to include in planning roadmaps - Stay up-to-date with advancements and the latest modeling techniques in the field - Publish your research findings in top conferences and journals About the team Our Prime Video Content Understanding team builds holistic media representations (e.g. descriptions of scenes, semantic embeddings) and apply them to new customer experiences supply chain problems. Our technology spans the entire Prime Video catalogue globally, and we enable instant recaps, skip intro timing, ad placement, search, and content moderation.
IN, HR, Gurugram
We're on a journey to build something new a green field project! Come join our team and build new discovery and shopping products that connect customers with their vehicle of choice. We're looking for a talented Senior Applied Scientist to join our team of product managers, designers, and engineers to design, and build innovative automotive-shopping experiences for our customers. This is a great opportunity for an experienced engineer to design and implement the technology for a new Amazon business. We are looking for a Applied Scientist to design, implement and deliver end-to-end solutions. We are seeking passionate, hands-on, experienced and seasoned Senior Applied Scientist who will be deep in code and algorithms; who are technically strong in building scalable computer vision machine learning systems across item understanding, pose estimation, class imbalanced classifiers, identification and segmentation.. You will drive ideas to products using paradigms such as deep learning, semi supervised learning and dynamic learning. As a Senior Applied Scientist, you will also help lead and mentor our team of applied scientists and engineers. You will take on complex customer problems, distill customer requirements, and then deliver solutions that either leverage existing academic and industrial research or utilize your own out-of-the-box but pragmatic thinking. In addition to coming up with novel solutions and prototypes, you will directly contribute to implementation while you lead. A successful candidate has excellent technical depth, scientific vision, project management skills, great communication skills, and a drive to achieve results in a unified team environment. You should enjoy the process of solving real-world problems that, quite frankly, haven’t been solved at scale anywhere before. Along the way, we guarantee you’ll get opportunities to be a bold disruptor, prolific innovator, and a reputed problem solver—someone who truly enables AI and robotics to significantly impact the lives of millions of consumers. Key job responsibilities Architect, design, and implement Machine Learning models for vision systems on robotic platforms Optimize, deploy, and support at scale ML models on the edge. Influence the team's strategy and contribute to long-term vision and roadmap. Work with stakeholders across , science, and operations teams to iterate on design and implementation. Maintain high standards by participating in reviews, designing for fault tolerance and operational excellence, and creating mechanisms for continuous improvement. Prototype and test concepts or features, both through simulation and emulators and with live robotic equipment Work directly with customers and partners to test prototypes and incorporate feedback Mentor other engineer team members. A day in the life - 6+ years of building machine learning models for retail application experience - PhD, or Master's degree and 6+ years of applied research experience - Experience programming in Java, C++, Python or related language - Experience with neural deep learning methods and machine learning - Demonstrated expertise in computer vision and machine learning techniques.
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 team member, 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! Key job responsibilities As an Applied Scientist in the Content Understanding Team, you will lead the end-to-end research and deployment of video and multi-modal models applied to a variety of downstream applications. More specifically, you will: - Work backwards from customer problems to research and design scientific approaches for solving them - Work closely with other scientists, engineers and product managers to expand the depth of our product insights with data, create a variety of experiments to determine the high impact projects to include in planning roadmaps - Stay up-to-date with advancements and the latest modeling techniques in the field - Publish your research findings in top conferences and journals About the team Our Prime Video Content Understanding team builds holistic media representations (e.g. descriptions of scenes, semantic embeddings) and apply them to new customer experiences supply chain problems. Our technology spans the entire Prime Video catalogue globally, and we enable instant recaps, skip intro timing, ad placement, search, and content moderation.
US, WA, Seattle
Do you want to re-invent how millions of people consume video content on their TVs, Tablets and Alexa? We are building a free to watch streaming service called Fire TV Channels (https://techcrunch.com/2023/08/21/amazon-launches-fire-tv-channels-app-400-fast-channels/). Our goal is to provide customers with a delightful and personalized experience for consuming content across News, Sports, Cooking, Gaming, Entertainment, Lifestyle and more. You will work closely with engineering and product stakeholders to realize our ambitious product vision. You will get to work with Generative AI and other state of the art technologies to help build personalization and recommendation solutions from the ground up. You will be in the driver's seat to present customers with content they will love. Using Amazon’s large-scale computing resources, you will ask research questions about customer behavior, build state-of-the-art models to generate recommendations and run these models to enhance the customer experience. You will participate in the Amazon ML community and mentor Applied Scientists and Software Engineers with a strong interest in and knowledge of ML. Your work will directly benefit customers and you will measure the impact using scientific tools.
US, MA, Boston
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Applied Scientist with a strong deep learning background, to build industry-leading technology with Large Language Models (LLMs) and multi-modal systems. You will support projects that work on technologies including multi-modal model alignment, moderation systems and evaluation. Key job responsibilities As an Applied Scientist with the AGI team, you will support the development of novel algorithms and modeling techniques, to advance the state of the art with LLMs. Your work will directly impact our customers in the form of products and services that make use of speech and language technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in generative artificial intelligence (GenAI). You are also expected to publish in top tier conferences. About the team The AGI team has a mission to push the envelope in LLMs and multimodal systems. Specifically, we focus on model alignment with an aim to maintain safety while not denting utility, in order to provide the best-possible experience for our customers.
IN, HR, Gurugram
Our customers have immense faith in our ability to deliver packages timely and as expected. A well planned network seamlessly scales to handle millions of package movements a day. It has monitoring mechanisms that detect failures before they even happen (such as predicting network congestion, operations breakdown), and perform proactive corrective actions. When failures do happen, it has inbuilt redundancies to mitigate impact (such as determine other routes or service providers that can handle the extra load), and avoids relying on single points of failure (service provider, node, or arc). Finally, it is cost optimal, so that customers can be passed the benefit from an efficiently set up network. Amazon Shipping is hiring Applied Scientists to help improve our ability to plan and execute package movements. As an Applied Scientist in Amazon Shipping, you will work on multiple challenging machine learning problems spread across a wide spectrum of business problems. You will build ML models to help our transportation cost auditing platforms effectively audit off-manifest (discrepancies between planned and actual shipping cost). You will build models to improve the quality of financial and planning data by accurately predicting ship cost at a package level. Your models will help forecast the packages required to be pick from shipper warehouses to reduce First Mile shipping cost. Using signals from within the transportation network (such as network load, and velocity of movements derived from package scan events) and outside (such as weather signals), you will build models that predict delivery delay for every package. These models will help improve buyer experience by triggering early corrective actions, and generating proactive customer notifications. Your role will require you to demonstrate Think Big and Invent and Simplify, by refining and translating Transportation domain-related business problems into one or more Machine Learning problems. You will use techniques from a wide array of machine learning paradigms, such as supervised, unsupervised, semi-supervised and reinforcement learning. Your model choices will include, but not be limited to, linear/logistic models, tree based models, deep learning models, ensemble models, and Q-learning models. You will use techniques such as LIME and SHAP to make your models interpretable for your customers. You will employ a family of reusable modelling solutions to ensure that your ML solution scales across multiple regions (such as North America, Europe, Asia) and package movement types (such as small parcel movements and truck movements). You will partner with Applied Scientists and Research Scientists from other teams in US and India working on related business domains. Your models are expected to be of production quality, and will be directly used in production services. You will work as part of a diverse data science and engineering team comprising of other Applied Scientists, Software Development Engineers and Business Intelligence Engineers. You will participate in the Amazon ML community by authoring scientific papers and submitting them to Machine Learning conferences. You will mentor Applied Scientists and Software Development Engineers having a strong interest in ML. You will also be called upon to provide ML consultation outside your team for other problem statements. If you are excited by this charter, come join us!