Chatbots and language models are something many people have probably come into contact with in recent months, whether in the workplace, university or classroom. All of these models build on research in areas such as Machine Learning and Natural Language Processing (NLP).
However, the rapid progress in Natural Language Processing also leads to the paradoxical situation that even top scientists often lose track of the current state of research: The available scientific literature is simply growing far too fast. This is also due to the fact that research is increasingly using machine learning algorithms and a flood of ever new language models, which further accelerate the scientific output. Against this backdrop, even AI professionals are finding it difficult to keep up with the latest developments – and a plethora of scientific papers.
A team from the TU Darmstadt is trying to find a solution to this problem. As of this year, their research project is being funded by Amazon. The project aims to create a “virtual research assistant” that will quickly and reliably help researchers close their own knowledge gaps by answering their questions. The assistant will pick out the right content from the mass of accessible scientific literature and provide it in dialog with the user as a natural language answer.
Particularly important to the AI researchers is ensuring the accuracy of the information provided. Many current chatbots powered by large language models can repeatedly fail to provide factually correct answers. For the virtual assistant, the researchers are working on a combination of large language models with so-called symbolic reasoning, which should prevent the generation of false information. This should also promote greater transparency in how the assistant arrives at its results.
The research project, entitled “Modeling Task-oriented Dialogues Grounded in Scientific Literature,” is being conducted at the Ubiquitous Knowledge Processing (UKP) Lab at TU Darmstadt in cooperation with Amazon Alexa Berlin. The first phase is planned for two years (2023-2025) with a budget in the low six figures. The financial support will also fund a PhD student position. The project is led by Prof. Dr. Iryna Gurevych, head of the UKP Lab and founding member of hessian.ai.
The findings from the project could not only facilitate the work of future AI researchers – they could potentially also find application in other fields with rapidly growing knowledge bases, for example in medical research. Because here, too, sifting through existing research takes a lot of time. The team expects this to have long-term and transformative effects for researchers and professionals.
The research grant from Amazon for the machine learning project is the second grant from the U.S. company to go to TU Darmstadt within two years: Professor Jan Peters' robotics research has already been funded with an Amazon Research Award since 2022.