Natural language processing
Natural language processing

Natural language processing

Artificial Intelligence Augmented and virtual reality Center for Bits and Atoms Computer science and technology Design DesignX Digital technology Electrical engineering and computer science (EECS) Graduate, postdoctoral Human-computer interaction Innovation and Entrepreneurship (I&E) MIT Morningside Academy for Design MIT Schwarzman College of Computing Natural language processing Profile Robotics School of Architecture and Planning School of Engineering Students Technology and society

Merging design and computer science in creative ways

MAD Fellow Alexander Htet Kyaw connects humans, machines, and the physical world using AI and augmented reality.

Artificial Intelligence Department of Defense (DoD) Lincoln Laboratory Logistics Natural language processing Security studies and military Software

Artificial intelligence enhances air mobility planning

Lincoln Laboratory is transitioning tools to the 618th Air Operations Center to streamline global transport logistics.

Algorithms Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology Electrical engineering and computer science (EECS) machine learning MIT Schwarzman College of Computing MIT-IBM Watson AI Lab National Science Foundation (NSF) Natural language processing Research School of Engineering Software Technology and society

Training LLMs to self-detoxify their language

A new method from the MIT-IBM Watson AI Lab helps large language models to steer their own responses toward safer, more ethical, value-aligned outputs.

Algorithms Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology computer-vision Electrical engineering and computer science (EECS) machine learning MIT Schwarzman College of Computing Natural language processing Quest for Intelligence Research Robotics School of Engineering

Teaching a robot its limits, to complete open-ended tasks safely

The “PRoC3S” method helps an LLM create a viable action plan by testing each step in a simulation. This strategy could eventually aid in-home robots to complete more ambiguous chore requests.

Artificial Intelligence Brain and cognitive sciences Internet Mental health Natural language processing Research School of Science social media

Study: Browsing negative content online makes mental health struggles worse

Researchers have developed a web plug-in to help those looking to protect their mental health make more informed decisions.

Algorithms Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology Electrical Engineering & Computer Science (eecs) Game theory Human-computer interaction machine learning MIT Schwarzman College of Computing MIT-IBM Watson AI Lab Natural language processing Research Robotics School of Engineering

Using ideas from game theory to improve the reliability of language models

A new “consensus game,” developed by MIT CSAIL researchers, elevates AI’s text comprehension and generation skills.

Artificial Intelligence Brain and cognitive sciences Center for Brains Minds and Machines Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology computer-vision Defense Advanced Research Projects Agency (DARPA) Department of Defense (DoD) Electrical Engineering & Computer Science (eecs) Human-computer interaction MIT Schwarzman College of Computing MIT-IBM Watson AI Lab National Science Foundation (NSF) Natural language processing Programming Programming languages Quest for Intelligence Research Robotics School of Engineering School of Science

Natural language boosts LLM performance in coding, planning, and robotics

Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.

Algorithms Artificial Intelligence Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology Electrical Engineering & Computer Science (eecs) Ethics Interview machine learning MIT Schwarzman College of Computing Natural language processing School of Engineering Technology and society

3 Questions: What you need to know about audio deepfakes

MIT CSAIL postdoc Nauman Dawalatabad explores ethical considerations, challenges in spear-phishing defense, and the optimistic future of AI-created voices across various sectors.

Artificial Intelligence Communications Computer Science and Artificial Intelligence Laboratory (CSAIL) Computer science and technology computer-vision Electrical Engineering & Computer Science (eecs) Graduate, postdoctoral Human-computer interaction machine learning MIT Schwarzman College of Computing MIT-IBM Watson AI Lab Natural language processing Research Robotics School of Engineering Students

Reasoning and reliability in AI

PhD students interning with the MIT-IBM Watson AI Lab look to improve natural language usage.

Artificial Intelligence Classes and programs Collaboration Data Electrical Engineering & Computer Science (eecs) Graduate, postdoctoral Human-computer interaction Industry Linguistics machine learning MIT Schwarzman College of Computing MIT-IBM Watson AI Lab Natural language processing Research School of Engineering School of Humanities Arts and Social Sciences Students

Leveraging language to understand machines

Master’s students Irene Terpstra ’23 and Rujul Gandhi ’22 use language to design new integrated circuits and make it understandable to robots.