Ruchira’s Homepage
🎓 Short Intro: Hello there! I’m a PhD Researcher in Natural Language Processing and AI, supervised by Dr. Anders Søgaard, in the CoAStaL Lab at the Department of Computer Science, University of Copenhagen. Additionally, I am involved with the Centre of Philosophy of AI, exploring the societal and ethical dimensions of AI.
🧠 Research Interests: My core research focus is on the evaluation of Large Language Models (LLMs), with a particular emphasis on assessing their diverse capabilities and humanlike behaviors. I aim to make these systems’ strengths and limitations more interpretable, measurable, and actionable for developers, policymakers, and end-users alike. To do so, I draw on interdisciplinary methods and insights from Artificial Intelligence, Machine Learning, Cognitive Science, Linguistics, and Social Sciences.
👥 Volunteering: I’m also a community lead at Cohere Labs , where I host talks, socials, and meetups to foster open-source research and collaborations in AI, emphasizing ethical and accessible approaches.
🚶🏽♀️➡️ Hobbies: When I’m not immersed in research, I enjoy reading about International Relations and Economics.
Research Updates
Publications
Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users
ACL 2025 (Main Conference)
Publication upcoming in ACL Anthology
→ Evaluates LLMs as accessibility tools for visually impaired users.
Investigating the Role of Modality and Training Objective on Representational Alignment Between Transformers and the Brain
UniReps Workshop @ NeurIPS 2024 (Proceedings Track)
Publication upcoming in Proceedings of Machine Learning Research (PMLR) → Evaluates representational alignment in LLMs and human FMRI.
Defining Knowledge: Bridging Epistemology and Large Language Models
EMNLP 2024 (Main Conference)
→ Explores the evaluation of knowledge in LLMs with perspectives from epistemology.
Peer-Reviewed Presentations
From Words to Worlds: Compositionality for Cognitive Architectures
LLMs & Cognition Workshop @ ICML 2024, Vienna
→ Evaluates reasoning and compositionality in LLMs.
The Completeness Problem: Beyond Human Metrics in Assessing Abilities of Cognitive Systems
Oral Presentation@ ACAIN 2024 (International Symposium on AI & Neuroscience)
→ Introduces a critical perspective on how we define and evaluate intelligence in AI.
Compositionality in Language Models: A Perspective in Changing Interpretations and Methods
Oral Presentation@ AIAI 2024 (Symposium on Agency and Intentions in AI)
→ Introduces a critical perspective on how we define and evaluate compositionality in AI.