alignAI
Aligning LLM Technologies with Societal Values
About alignAI
About the project
The alignAI Doctoral Network will train 16 doctoral candidates (DCs) to work in the international and highly interdisciplinary field of LLM research and development. The core of the project focuses on the alignment of LLMs with human values, identifying relevant values and methods for alignment implementation. Two principles provide a foundation for the approach. First, explainability is a key enabler for all aspects of trustworthiness, accelerating development, promoting usability, and facilitating human oversight and auditing of LLMs. Second, fairness is a key aspect of trustworthiness, facilitating access to AI applications and ensuring equal impact of AI-driven decision-making. The practical relevance of the project is ensured by three use cases in education, positive mental health, and news consumption. This approach allows us to develop specific guidelines and test prototypes and tools to promote value alignment. We follow a unique methodological approach, with DCs from social sciences and humanities “twinned” with DCs from technical disciplines for each use case (8 DCs in total), while the other 8 DCs carry out horizontal research across the use cases.
About Large Language Models
Large Language Models (LLMs) are trained on broad data, using self-supervision at scale, to complete a wide range of tasks. Wider use of LLMs has risen in recent months due to applications such as ChatGPT. Although LLMs bring many opportunities to improve our everyday lives, the impacts on humans and society have not yet been prioritized or fully understood. Given the rapid development of these tools, the risk of negative implications is significant if LLMs are not developed and deployed in a way that is aligned with human values and responds to individual needs and preferences. To mitigate any negative consequences, academia, in close collaboration with industry, needs to train the next generation of researchers to understand the complexities of the socio-technical implications surrounding the use of LLMs.
Project Map
The alignAI project is built around a highly interdisciplinary training program
and research methodology designed to achieve the DN’s five research objectives:
- O1. Establish a unique doctoral training programme (i) equipping DCs with the capacity to work in interdisciplinary environments, (ii) providing high quality scientific training, (iii) equipping DCs with communication capacities and (iv) Disseminating knowledge beyond the beneficiary institutions
- O2. Identify the human values and user requirements/preferences that LLMs should align with
- O3. Explore implementable ways for applying the principles of explainability (XAI) and fairness in
the specific context of LLM use to enable alignment with values identified in RIO1 - O4. Design and build value aligned LLM prototype tools based on outcomes from RIO1 and RIO2
- O5. Test & validate the technical prototype tools from RIO3 and the non-technical
tools/methods/models from RIO1 and RIO2 - O6. Translate learnings from RIO1-RIO4 into research outputs, contextualising an “enabling
environment” for value-aligned LLMs
The doctoral training objective O1 is described in detail in Section 1.3.
The five research objectives will be addressed in a context-specific way throughout the project by
investigating them as part of three use-cases in: (i) Education, (ii) Positive Mental Health and (iii) Online
News Consumption. Fig. 3. presents the proposed research methodology. This is followed by a detailed
description of the research activities and their relevance for the project objectives.
Newsroom
Juliet Arthur Presents on Behalf of Ama Branoa Banful at the 2026 The Responsible AI Forum (TRAIF)
On May 19th, 2026, Juliet Arthur presented on behalf of Generative AI, LLMs and Societal Value Alignment track travel grant winner Ama Branoa Banful at the 2026 The Responsible AI Forum (TRAIF) held at Amerikahaus in Munich. During the AI Governance in Institutional and Regulatory Contexts session, Ms. Arthur presented: “Governing the Use of Generative AI in Public and Civic Decision-Making Contexts”.
David Torabi Presents on Behalf of Darius Torabi at the 2026 The Responsible AI Forum (TRAIF)
On May 19th, 2026, David Torabi presented on behalf of Generative AI, LLMs and Societal Value Alignment track travel grant winner Darius Torabi at the 2026 The Responsible AI Forum (TRAIF) held at Amerikahaus in Munich. During the Philosophical and Technical Foundations of Value Alignment session, Mr. Torabi presented: “Why Shared Values Are Hard to Share”.
Dr. Youngsam Chun Presents at the 2026 The Responsible AI Forum (TRAIF)
On May 19th, 2026, Generative AI, LLMs and Societal Value Alignment track travel grant winner Dr. Youngsam Chun presented at the 2026 The Responsible AI Forum (TRAIF) held at Amerikahaus in Munich. During the Philosophical and Technical Foundations of Value Alignment session, Dr. Chun presented: “MORAL-GRAPH: A Geometric and Graph-based Framework for Human-LLM Value Alignment”.
When AI Becomes a Learning Partner: How Can We Preserve Learner Agency in Education?
A student sits down to write an essay, solve a programming exercise or prepare for an exam. Instead of searching through textbooks or waiting for office hours, they open an AI assistant. The system offers explanations, suggests what to try next and responds when the student asks follow-up questions. In many ways, this looks like a breakthrough for education: support is available at any time, at low cost and in a conversational form.
Reflections from a Research Secondment at the Eindhoven University of Technology
From the end of March to beginning of June 2026, TUM IEAI DC Julia Li completed a research secondment at Eindhoven University of Technology (TU/e) in the Netherlands.
Q&A with DC Julia Li
In this video interview, we speak with Julia Li, doctoral candidate in the alignAI project at the Technical University of Munich Institute for Ethics in Artificial Intelligence. She introduces herself and her research on human values and AI alignment, explaining what inspired her to join alignAI and which aspects of aligning AI with human values she finds most compelling.