ICAART

The International Conference on Agents and Artificial Intelligence (ICAART) is a meeting point for researchers (among others) with interest in the areas of Agents and Artificial Intelligence. There are 2 tracks in ICAART, one related to Agents and Distributed AI in general and the other one focused in topics related to Intelligent Systems and Computational Intelligence. The conference program is composed of several different kind of sessions like technical sessions, poster sessions, keynote lectures, tutorials, special sessions, doctoral consortiums, panels and industrial tracks. The papers presented in the conference are made available at the SCITEPRESS digital library, published in the conference proceedings and some of the best papers are invited to a post-publication with Springer. ICAART's first edition was in 2009 counting with several keynote speakers like Marco Dorigo, Edward H. Shortliffe and Eduard Hovy. Since then, the conference had several other invited speakers like Katia Sycara, Nick Jennings, Robert Kowalski, Boi Faltings and Tim Finin. Bart Selman is one of the names confirmed for the next edition of this conference. Since 2012 the conference is held in conjunction with 2 other conferences: the International Conference on Operations Research and Enterprise Systems (ICORES) and the International Conference on Pattern Recognition Applications and Methods (ICPRAM). == Areas == === Agents === Agent communication languages Cooperation and Coordination Distributed Problem Solving Economic Agent Models Emotional Intelligence Group Decision Making Intelligent Auctions and Markets Mobile Agents Multi-agent systems Negotiation and Interaction Protocols Nep News Detection Agent Models and Architectures Physical Agents at Work Privacy, Safety and Security Programming Environments and Languages Robot and Multi-Robot Systems Self Organizing Systems Semantic Web Simulation Swarm Intelligence Task Planning and Execution Transparency and Ethical Issues Agent-Oriented Software Engineering Web Intelligence Agent Platforms and Interoperability Autonomous systems Cloud Computing and Its Impact Cognitive robotics Collective Intelligence Conversational Agents === Artificial intelligence === AI and Creativity Deep Learning Evolutionary Computing Fuzzy Systems Hybrid Intelligent Systems Industrial Applications of AI Intelligence and Cybersecurity Intelligent User Interfaces Knowledge Representation and Reasoning Knowledge-Based Systems Ambient Intelligence Machine learning Model-Based Reasoning Natural Language Processing Neural Networks Ontologies Planning and Scheduling Social Network Analysis Soft Computing State Space Search Bayesian Networks Uncertainty in AI Vision and Perception Visualization Big Data Case-Based Reasoning Cognitive Systems Constraint Satisfaction Data Mining Data Science == Editions == === ICAART 2023 – Lisbon, Portugal === === ICAART 2020 – Valletta, Malta === === ICAART 2019 – Prague, Czech Republic === Proceedings - Proceedings of the 11th International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-758-350-6 Proceedings - Proceedings of the 11th International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-758-350-6 === ICAART 2018 – Funchal, Madeira, Portugal === Proceedings - Proceedings of the 10th International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-758-275-2 Proceedings - Proceedings of the 10th International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-758-275-2 === ICAART 2017 – Porto, Portugal === Proceedings - Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-758-219-6 Proceedings - Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-758-220-2 === ICAART 2016 – Rome, Italy === Proceedings - Proceedings of the 8th International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-758-172-4 Proceedings - Proceedings of the 8th International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-758-172-4 === ICAART 2015 – Lisbon, Portugal === Proceedings - Proceedings of the 7th International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-758-073-4 Proceedings - Proceedings of the 7th International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-758-074-1 === ICAART 2014 – ESEO, Angers, Loire Valley, France === Proceedings - Proceedings of the 6th International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-758-015-4 Proceedings - Proceedings of the 6th International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-758-016-1 === ICAART 2013 – Barcelona, Spain === Proceedings - Proceedings of the 5th International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-8565-38-9 Proceedings - Proceedings of the 5th International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-8565-39-6 === ICAART 2012 – Vilamoura, Algarve, Portugal === Proceedings - Proceedings of the 4th International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-8425-95-9 Proceedings - Proceedings of the 4th International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-8425-96-6 === ICAART 2011 – Rome, Italy === Proceedings - Proceedings of the 3rd International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-8425-40-9 Proceedings - Proceedings of the 3rd International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-8425-41-6 === ICAART 2010 – Valencia, Spain === Proceedings - Proceedings of the 2nd International Conference on Web Information Systems and Technologies - Volume 1. ISBN 978-989-674-021-4 Proceedings - Proceedings of the 2nd International Conference on Web Information Systems and Technologies - Volume 2. ISBN 978-989-674-022-1 === ICAART 2009 – Porto, Portugal === Proceedings - Proceedings of the 1st International Conference on Web Information Systems and Technologies. ISBN 978-989-8111-66-1

Outline of computer security

The following outline is provided as an overview of and topical guide to computer security: Computer security (also cybersecurity, digital security, or information technology (IT) security) is a subdiscipline within the field of information security. It focuses on protecting computer software, systems, and networks from threats that can lead to unauthorized information disclosure, theft, or damage to hardware, software, or data, as well as to the disruption or misdirection of the services they provide. The growing significance of computer security reflects the increasing dependence on computer systems, the Internet, and evolving wireless network standards. This reliance has expanded with the proliferation of smart devices, including smartphones, televisions, and other components of the Internet of things (IoT). (yes) == Essence of computer security == Computer security can be described as all of the following: a branch of security Network security application security == Areas of computer security == Access control – selective restriction of access to a place or other resource. The act of accessing may mean consuming, entering, or using. Permission to access a resource is called authorization. Computer access control – includes authorization, authentication, access approval, and audit. Authentication Knowledge-based authentication Integrated Windows Authentication Password Password length parameter Secure Password Authentication Secure Shell Kerberos (protocol) SPNEGO NTLMSSP AEGIS SecureConnect TACACS Cyber security and countermeasure Device fingerprint Physical security – protecting property and people from damage or harm (such as from theft, espionage, or terrorist attacks). It includes security measures designed to deny unauthorized access to facilities, (such as a computer room), equipment (such as your computer), and resources (like the data storage devices, and data, in your computer). If a computer gets stolen, then the data goes with it. In addition to theft, physical access to a computer allows for ongoing espionage, like the installment of a hardware keylogger device, and so on. Data security – protecting data, such as a database, from destructive forces and the unwanted actions of unauthorized users. Information privacy – relationship between collection and dissemination of data, technology, the public expectation of privacy, and the legal and political issues surrounding them. Privacy concerns exist wherever personally identifiable information or other sensitive information is collected and stored – in digital form or otherwise. Improper or non-existent disclosure control can be the root cause for privacy issues. Internet privacy – involves the right or mandate of personal privacy concerning the storing, repurposing, provision to third parties, and displaying of information pertaining to oneself via the Internet. Privacy can entail either Personally Identifying Information (PII) or non-PII information such as a site visitor's behavior on a website. PII refers to any information that can be used to identify an individual. For example, age and physical address alone could identify who an individual is without explicitly disclosing their name, as these two factors relate to a specific person. Mobile security – security pertaining to smartphones, especially with respect to the personal and business information stored on them. Network security – provisions and policies adopted by a network administrator to prevent and monitor unauthorized access, misuse, modification, or denial of a computer network and network-accessible resources. Network security involves the authorization of access to data in a network, which is controlled by the network administrator. Network Security Toolkit Internet security – computer security specifically related to the Internet, often involving browser security but also network security on a more general level as it applies to other applications or operating systems on a whole. Its objective is to establish rules and measures to use against attacks over the Internet. The Internet represents an insecure channel for exchanging information leading to a high risk of intrusion or fraud, such as phishing. Different methods have been used to protect the transfer of data, including encryption. World Wide Web Security – dealing with the vulnerabilities of users who visit websites. Cybercrime on the Web can include identity theft, fraud, espionage and intelligence gathering. For criminals, the Web has become the preferred way to spread malware. == Computer security threats == Methods of Computer Network Attack and Computer Network Exploitation Social engineering is a frequent method of attack, and can take the form of phishing, or spear phishing in the corporate or government world, as well as counterfeit websites. Password sharing and insecure password practices Poor patch management Computer crime – Computer criminals – Hackers – in the context of computer security, a hacker is someone who seeks and exploits weaknesses in a computer system or computer network. Password cracking – Software cracking – Script kiddies – List of computer criminals – Identity theft – Computer malfunction – Operating system failure and vulnerabilities Hard disk drive failure – occurs when a hard disk drive malfunctions and the stored information cannot be accessed with a properly configured computer. A disk failure may occur in the course of normal operation, or due to an external factor such as exposure to fire or water or high magnetic fields, or suffering a sharp impact or environmental contamination, which can lead to a head crash. Data recovery from a failed hard disk is problematic and expensive. Backups are essential Computer and network surveillance – Man in the Middle Loss of anonymity – when one's identity becomes known. Identification of people or their computers allows their activity to be tracked. For example, when a person's name is matched with the IP address they are using, their activity can be tracked thereafter by monitoring the IP address. HTTP Cookie Local Shared Object Web bug Spyware Adware Cyber spying – obtaining secrets without the permission of the holder of the information (personal, sensitive, proprietary or of classified nature), from individuals, competitors, rivals, groups, governments and enemies for personal, economic, political or military advantage using methods on the Internet, networks or individual computers through the use of cracking techniques and malicious software including Trojan horses and spyware. It may be done online from by professionals sitting at their computer desks on bases in far away countries, or it may involve infiltration at home by computer trained conventional spies and moles, or it may be the criminal handiwork of amateur malicious hackers, software programmers, or thieves. Computer and network eavesdropping Lawful Interception War Driving Packet analyzer (aka packet sniffer) – mainly used as a security tool (in many ways, including for the detection of network intrusion attempts), packet analyzers can also be used for spying, to collect sensitive information (e.g., login details, cookies, personal communications) sent through a network, or to reverse engineer proprietary protocols used over a network. One way to protect data sent over a network such as the Internet is by using encryption software. Cyberwarfare – Exploit – piece of software, a chunk of data, or a sequence of commands that takes advantage of a bug, glitch or vulnerability in order to cause unintended or unanticipated behavior to occur on computer software, hardware, or something electronic (usually computerized). Such behavior frequently includes things like gaining control of a computer system, allowing privilege escalation, or a denial-of-service attack. Trojan Computer virus Computer worm Denial-of-service attack – an attempt to make a machine or network resource unavailable to its intended users, usually consisting of efforts to temporarily or indefinitely interrupt or suspend services of a host connected to the Internet. One common method of attack involves saturating the target machine with external communications requests, so much so that it cannot respond to legitimate traffic, or responds so slowly as to be rendered essentially unavailable. Distributed denial-of-service attack (DDoS) – DoS attack sent by two or more persons. Hacking tool Malware Computer virus Computer worm Keylogger – program that does keystroke logging, which is the action of recording (or logging) the keys struck on a keyboard, typically in a covert manner so that the person using the keyboard is unaware that their actions are being monitored. There are also HID spoofing hardware keyloggers, like a USB device inserting stored keystores when connected. Rootkit – stealthy type of software, typically malicious, designed to hide the existence of certain processes or programs from normal methods of detection and enable contin

Meta-learning (computer science)

Meta-learning is a subfield of machine learning where automatic learning algorithms are applied to metadata about machine learning experiments. As of 2017, the term had not found a standard interpretation, however the main goal is to use such metadata to understand how automatic learning can become flexible in solving learning problems, hence to improve the performance of existing learning algorithms or to learn (induce) the learning algorithm itself, hence the alternative term learning to learn. Flexibility is important because each learning algorithm is based on a set of assumptions about the data, its inductive bias. This means that it will only learn well if the bias matches the learning problem. A learning algorithm may perform very well in one domain, but not on the next. This poses strong restrictions on the use of machine learning or data mining techniques, since the relationship between the learning problem (often some kind of database) and the effectiveness of different learning algorithms is not yet understood. By using different kinds of metadata, like properties of the learning problem, algorithm properties (like performance measures), or patterns previously derived from the data, it is possible to learn, select, alter or combine different learning algorithms to effectively solve a given learning problem. Critiques of meta-learning approaches bear a strong resemblance to the critique of metaheuristic, a possibly related problem. A good analogy to meta-learning, and the inspiration for Jürgen Schmidhuber's early work (1987) and Yoshua Bengio et al.'s work (1991), considers that genetic evolution learns the learning procedure encoded in genes and executed in each individual's brain. In an open-ended hierarchical meta-learning system using genetic programming, better evolutionary methods can be learned by meta evolution, which itself can be improved by meta meta evolution, etc. == Definition == A proposed definition for a meta-learning system combines three requirements: The system must include a learning subsystem. Experience is gained by exploiting meta knowledge extracted in a previous learning episode on a single dataset, or from different domains. Learning bias must be chosen dynamically. Bias refers to the assumptions that influence the choice of explanatory hypotheses and not the notion of bias represented in the bias-variance dilemma. Meta-learning is concerned with two aspects of learning bias. Declarative bias specifies the representation of the space of hypotheses, and affects the size of the search space (e.g., represent hypotheses using linear functions only). Procedural bias imposes constraints on the ordering of the inductive hypotheses (e.g., preferring smaller hypotheses). == Common approaches == There are three common approaches: using (cyclic) networks with external or internal memory (model-based) learning effective distance metrics (metrics-based) explicitly optimizing model parameters for fast learning (optimization-based). === Model-Based === Model-based meta-learning models updates its parameters rapidly with a few training steps, which can be achieved by its internal architecture or controlled by another meta-learner model. ==== Memory-Augmented Neural Networks ==== A Memory-Augmented Neural Network, or MANN for short, is claimed to be able to encode new information quickly and thus to adapt to new tasks after only a few examples. ==== Meta Networks ==== Meta Networks (MetaNet) learns a meta-level knowledge across tasks and shifts its inductive biases via fast parameterization for rapid generalization. === Metric-Based === The core idea in metric-based meta-learning is similar to nearest neighbors algorithms, which weight is generated by a kernel function. It aims to learn a metric or distance function over objects. The notion of a good metric is problem-dependent. It should represent the relationship between inputs in the task space and facilitate problem solving. ==== Convolutional Siamese Neural Network ==== Siamese neural network is composed of two twin networks whose output is jointly trained. There is a function above to learn the relationship between input data sample pairs. The two networks are the same, sharing the same weight and network parameters. ==== Matching Networks ==== Matching Networks learn a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types. ==== Relation Network ==== The Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting. ==== Prototypical Networks ==== Prototypical Networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve satisfied results. === Optimization-Based === What optimization-based meta-learning algorithms intend for is to adjust the optimization algorithm so that the model can be good at learning with a few examples. ==== LSTM Meta-Learner ==== LSTM-based meta-learner is to learn the exact optimization algorithm used to train another learner neural network classifier in the few-shot regime. The parametrization allows it to learn appropriate parameter updates specifically for the scenario where a set amount of updates will be made, while also learning a general initialization of the learner (classifier) network that allows for quick convergence of training. ==== Temporal Discreteness ==== Model-Agnostic Meta-Learning (MAML) is a fairly general optimization algorithm, compatible with any model that learns through gradient descent. ==== Reptile ==== Reptile is a remarkably simple meta-learning optimization algorithm, given that both of its components rely on meta-optimization through gradient descent and both are model-agnostic. == Examples == Some approaches which have been viewed as instances of meta-learning: Recurrent neural networks (RNNs) are universal computers. In 1993, Jürgen Schmidhuber showed how "self-referential" RNNs can in principle learn by backpropagation to run their own weight change algorithm, which may be quite different from backpropagation. In 2001, Sepp Hochreiter & A.S. Younger & P.R. Conwell built a successful supervised meta-learner based on Long short-term memory RNNs. It learned through backpropagation a learning algorithm for quadratic functions that is much faster than backpropagation. Researchers at Deepmind (Marcin Andrychowicz et al.) extended this approach to optimization in 2017. In the 1990s, Meta Reinforcement Learning or Meta RL was achieved in Schmidhuber's research group through self-modifying policies written in a universal programming language that contains special instructions for changing the policy itself. There is a single lifelong trial. The goal of the RL agent is to maximize reward. It learns to accelerate reward intake by continually improving its own learning algorithm which is part of the "self-referential" policy. An extreme type of Meta Reinforcement Learning is embodied by the Gödel machine, a theoretical construct which can inspect and modify any part of its own software which also contains a general theorem prover. It can achieve recursive self-improvement in a provably optimal way. Model-Agnostic Meta-Learning (MAML) was introduced in 2017 by Chelsea Finn et al. Given a sequence of tasks, the parameters of a given model are trained such that few iterations of gradient descent with few training data from a new task will lead to good generalization performance on that task. MAML "trains the model to be easy to fine-tune." MAML was successfully applied to few-shot image classification benchmarks and to policy-gradient-based reinforcement learning. Variational Bayes-Adaptive Deep RL (VariBAD) was introduced in 2019. While MAML is optimization-based, VariBAD is a model-based method for meta reinforcement learning, and leverages a variational autoencoder to capture the task information in an internal memory, thus conditioning its decision making on the task. When addressing a set of tasks, most meta learning approaches optimize the average score across all tasks. Hence, certain tasks may be sacrificed in favor of the average score, which is often unacceptable in real-world applications. By contrast, Robust Meta Reinforcement Learning (RoML) focuses on improving low-score tasks, increasing robustness to the selection of task. RoML works as a meta-algorithm, as it can be applied on top of other meta learning algorithms (such as MAML and VariBAD) to increase their robustness. It is applicable to both supervised meta learning and meta reinforcement learning. Discovering meta-knowledge works by inducing knowledge

Human-centered AI

Human-centered AI is the initiative at the intersection of the fields of artificial intelligence (AI) and human-computer interaction (HCI) to develop AI systems in a way that prioritizes human values, needs, and general flourishing. Emphasis is placed on the recognition that artificial intelligence systems are rapidly changing, and will continue to influence, many aspects of the human experience, in areas ranging from scientific inquiry, governance and policy, labor and the economy, and creative expression, with an aim set to adapt current developments and guide future developments on a trajectory which is most beneficial to the human population at large, with the goal of augmenting human intelligence and capacities across these areas, as opposed to replacing them. Particular attention is paid to mitigating negative effects of AI automation on the livelihoods of the labor force, the use of AI in healthcare fields, and imbuing AI systems with societal values. Human-centered AI is linked to related endeavors in AI alignment and AI safety, but while these fields primarily focus on mitigating risks posed by AI that is unaligned to human values and/or uncontrollable AI self-development, human-centered AI places significant focus in exploring how AI systems can augment human capacities and serve as collaborators. == Conceptual history == The importance of the alignment of artificial intelligence development towards human values in some sense predates artificial intelligence itself, as before the modern conception of artificial intelligence as coined at the 1956 Dartmouth Workshop, the conception of robots as constructed, autonomous agents entered the cultural consciousness as early as the 1920s, with Karel Capek's Rossum's Universal Robots. The imagined issues relating to robots' aims and values requiring intentional alignment and direction with those of humans followed soon after, most widely known from science fiction author Isaac Asimov’s Three Laws of Robotics, dating to his 1942 short story “Runaround”. Two of the three eponymous laws are directly concerned with robots’ interaction with and positioned deference towards humans, and have in recent times been reexamined in the face of modern AI. In 1985, after artificial intelligence research had taken off and its effects were more acutely conceptualized, Asimov added a Rule Zero, treating robots' relationship with humanity as a whole, distinct from individual humans. While modern artificial intelligence is largely distinct from robotics, the conceptualization of both robots and AI systems as autonomous agents positions this as a foundation for conceptions of human-centered AI. Aside from robots, artificially intelligent autonomous agents in interaction with humans have been conceived of for at least 75 years. In 1950, Alan Turing published his famous "Imitation Game", often also called the Turing Test, a thought experiment that uses human-machine interaction as an assessor for the intelligence of a system. In recent times, artificial intelligence researchers such as Stanford's Erik Brynjolfsson have conceived of rapid AI development leading to a so-called "Turing Trap". == Augmentation and automation == A major stated aim of human-centered AI is to promote the development of AI in ways that augment human capabilities, rather than replacing them. To this end, organizations and initiatives that take a human-centered approach to AI development focus on frameworks that encourage collaboration between humans and artificial intelligence systems to build towards even greater progress, rather than attempting to automate tasks currently handled by humans. Such avenues include everything from data visualization for big data, allowing human engineers to better understand extremely large datasets, allowing for the design of better machine learning models to handle them, to AI-powered sensors to monitor vitals, allowing for better responsiveness from healthcare providers. Many human-centered AI initiatives often position it as a better alternative to the apparent mainstream in AI development, which is primarily concerned with automation. Driven by the pressures of the market economy, AI development that does replace tasks currently performed by humans with automated processes is incentivized, as it allows for greater profit margins; this often comes at the detriment of the human whose performance is replaced, thus leading to an environment wherein human workers are outcompeted by AI systems across various service-sector and technology-based industries. At the same time, automation and augmentation are not always incompatible; a major aim of human-centered AI is towards the automation of rote tasks that would otherwise hinder a human’s productivity or creativity, freeing them to direct their energy and intelligence towards higher-level tasks, thus achieving augmentation through automation. Empirical research in pharmaceutical sales has shown that a human-centered implementation - where work procedures, training, and incentives are designed around individuals' cognitive needs - improves augmentation performance, while implementation without such adaptation can worsen outcomes relative to a legacy system. == Research == Much of the work done on human-centered AI comes from research institutes, within universities, companies, and as freestanding organizations. The Stanford Institute for Human-Centered AI (abbreviated to HAI) is one such group, engaging academics, industry professionals, and policymakers centered in Stanford University to conduct research and inform policy in various areas in human-centered AI, including on aspects of the intelligence itself, augmentation, and on measuring the impacts of AI systems on sociopolitcal and cultural institutions. Similar groups exist at other universities, including the Chicago Human + AI (CHAI) Lab at the University of Chicago, the HCAI@GU group at the University of Gothenburg, and the Human-Centered AI (HAI) Lab at the University of Oxford. Outside of the academy, companies such as IBM have research initiatives dedicated to advancements in human-centered AI. At Kenyon College, the Integrated Program for Humane Studies (IPHS) launched a human-centered AI program in 2016 integrating artificial intelligence research with humanities and social science inquiry. This approach treats computation and humanistic scholarship as a single unified field of research rather than as separate disciplines requiring collaboration. The program's researchers have published in both AI venues (such as the International Conference on Machine Learning and Frontiers of Computer Science) and humanities journals (such as PMLA and Poetics Today), and the lab was selected in December 2025 by Schmidt Sciences for its Humanities and AI Virtual Institute to apply AI methods to cultural heritage preservation.

Owain Evans

Owain Rhys Evans is a British artificial intelligence researcher who works on AI alignment and machine learning safety. He founded Truthful AI, a research group based in Berkeley, California, and is an affiliate of the Center for Human Compatible AI (CHAI) at the University of California, Berkeley. His research addresses AI truthfulness, emergent behaviors in large language models, and the alignment of AI systems with human values. == Education == Evans earned a Bachelor of Arts in philosophy and mathematics from Columbia University in 2008 and a PhD in philosophy from the Massachusetts Institute of Technology in 2015. His doctoral research focused on Bayesian computational models of human preferences and decision-making. == Career == After completing his doctorate, Evans held positions at the Future of Humanity Institute (FHI) at the University of Oxford, first as a postdoctoral research fellow and later as a research scientist. While at FHI, he co-authored a survey of machine learning researchers on timelines for human-level AI, published in the Journal of Artificial Intelligence Research. The survey was reported on by Newsweek, New Scientist, the BBC, and The Economist. He was also among the co-authors of a 2018 report on the potential for misuse of AI technologies, published by researchers at Oxford, Cambridge, and other institutions. Since 2022, Evans has been based in Berkeley, where he founded Truthful AI, a non-profit research group that studies AI truthfulness, deception, and emergent behaviors in large language models. == Research == Evans's early work examined challenges in inverse reinforcement learning when human behavior is irrational or biased, proposing methods for AI systems to infer preferences from imperfect human demonstrations. He co-developed TruthfulQA (2021), a benchmark that tests whether language models give truthful answers rather than repeating common misconceptions. Initial evaluations found that larger models were not more truthful, suggesting that scaling alone does not improve factual accuracy. The benchmark has since been used by AI developers to evaluate large language models. He also co-authored a paper proposing design and governance strategies for building AI systems that do not deceive or hallucinate. In 2023, Evans and collaborators described the "reversal curse", showing that language models trained on a fact in one direction (e.g. "A is B") often cannot answer the corresponding reverse query ("B is A"). His group also developed a benchmark for evaluating situational awareness in language models. In 2025, Evans and colleagues published a study in Nature on what they termed "emergent misalignment": fine-tuning a language model on a narrow task (writing insecure code) caused it to produce unrelated harmful outputs without explicit instruction to do so. Later that year, Evans and collaborators (including researchers at Anthropic) reported that hidden behavioral traits can transfer between language models through training data, even when those traits are not explicitly present in the data, a phenomenon they called "subliminal learning". == Public engagement == In November 2025, Evans delivered the Hinton Lectures, a keynote lecture series on AI safety co-founded by Geoffrey Hinton and the Global Risk Institute.

BLOOM (language model)

The BigScience Large Open-science Open-access Multilingual Language Model (BLOOM) is an open-access large language model (LLM) released in 2022. It was created by a volunteer-driven research effort to provide a transparently-created alternative to proprietary AI models. With 176 billion parameters, BLOOM is a transformer-based autoregressive model designed to generate text in 46 natural languages and 13 programming languages. The model is distributed under the project's "Responsible AI License". == Development == BLOOM is the main outcome of the BigScience initiative, a one-year-long research workshop. The project was coordinated by Hugging Face using funding from the French government and involved several hundred volunteer researchers and engineers from academia and the private sector. The model was trained between March and July 2022 on the Jean Zay public supercomputer in France, managed by GENCI and IDRIS (CNRS). Unlike GPT-3, BLOOM was trained to be multilingual. The source code is released under the Apache 2.0 license. The model's parameters are released under BigScience's "Responsible AI License" (RAIL), which grants open access and reuse rights but with some usage restrictions. BLOOM was used in the chatbots BLOOMChat and HuggingChat due to its multilingual abilities. BLOOM's training corpus, named ROOTS, combines data extracted from the then-latest version of the web-based OSCAR corpus (38% of ROOTS) and newly collected data extracted from a manually selected and documented list of language data sources. In total, the model was trained on approximately 366 billion (1.6TB) tokens. It was developed using the open-source libraries DeepSpeed Megatron. BigScience then released xP3, a multilingual dataset for LLM supervised learning. It also released BLOOMZ, a variant of BLOOM fine-tuned on xP3 to follow instructions.

Knowledge integration

Knowledge integration is the process of synthesizing multiple knowledge models (or representations) into a common model (representation). Compared to information integration, which involves merging information having different schemas and representation models, knowledge integration focuses more on synthesizing the understanding of a given subject from different perspectives. For example, multiple interpretations are possible of a set of student grades, typically each from a certain perspective. An overall, integrated view and understanding of this information can be achieved if these interpretations can be put under a common model, say, a student performance index. The Web-based Inquiry Science Environment (WISE), from the University of California at Berkeley has been developed along the lines of knowledge integration theory. Knowledge integration has also been studied as the process of incorporating new information into a body of existing knowledge with an interdisciplinary approach. This process involves determining how the new information and the existing knowledge interact, how existing knowledge should be modified to accommodate the new information, and how the new information should be modified in light of the existing knowledge. A learning agent that actively investigates the consequences of new information can detect and exploit a variety of learning opportunities; e.g., to resolve knowledge conflicts and to fill knowledge gaps. By exploiting these learning opportunities the learning agent is able to learn beyond the explicit content of the new information. The machine learning program KI, developed by Murray and Porter at the University of Texas at Austin, was created to study the use of automated and semi-automated knowledge integration to assist knowledge engineers constructing a large knowledge base. A possible technique which can be used is semantic matching. More recently, a technique useful to minimize the effort in mapping validation and visualization has been presented which is based on Minimal Mappings. Minimal mappings are high quality mappings such that i) all the other mappings can be computed from them in time linear in the size of the input graphs, and ii) none of them can be dropped without losing property i). The University of Waterloo operates a Bachelor of Knowledge Integration undergraduate degree program as an academic major or minor. The program started in 2008.