Research Output

Publications

Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives
Ruchira Dhar, Qiwei Peng, Anders Søgaard
Published at The 15th Joint Conference on Lexical and Computational Semantics (*SEM), ACL 2026

Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Research
Ninell Oldenburg, Ruchira Dhar, Anders Søgaard
Published at AAAI Conference, 2026 (Oral, Alignment Track)

Beyond Technocratic XAI: The Who, What & How in Explanation Design
Ruchira Dhar , Stephanie Brandl, Ninell Oldenburg, Anders Søgaard
Published at AAAI/ACM AI, Ethics, & Society (AIES) Conference, 2025

Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users
Antonia Karamolegkou, Malvina Nikandrou, Georgios Pantazopoulos, Danae Sanchez Villegas, Phillip Rust, Ruchira Dhar, Daniel Hershcovich, Anders Søgaard
Published at Association for Computational Linguistics (ACL), 2025

Investigating the Role of Modality and Training Objective on Representational Alignment Between Transformers and the Brain
Hyewon Willow Han, Ruchira Dhar, Qingqing Yang, Maryam Hoseini Behbahani, Maria Alejandra Martinez Ortiz, Tolulope Samuel Oladele, Diana C Dima, Hsin-Hung Li, Anders Søgaard, Yalda Mohsenzadeh
Published at UniReps Workshop @NeurIPS 2024 via Proceedings of Machine Learning Research (PMLR), 2024

Defining Knowledge: Bridging Epistemology and Large Language Models
Constanza Fierro, Ruchira Dhar, Filippos Stamatiou, Nicolas Garneau, Anders Søgaard
Published at Empirical Methods in Natural Language Processing (EMNLP), 2024

Presentations

On the Measure of a Model: From Intelligence to Generality
Ruchira Dhar, Ninell Oldenburg, Anders Søgaard
Accepted at The Science of Benchmarking and Evaluating AI Workshop @ EurIPS Conference, 2025

EvalCards: A Framework for Standardized Evaluation Reporting
Ruchira Dhar, Danae Sanchez Villegas, Antonia Karamolegkou, Alice Schiavone, Yifei Yuan, Xinyi Chen, Jiaang Li, Stella Frank, Laura De Grazia, Monorama Swain, Stephanie Brandl, Daniel Hershcovich, Anders Søgaard, Desmond Elliott
Accepted at The Science of Benchmarking and Evaluating AI Workshop @ EurIPS Conference, 2025

From Words to Worlds: Compositionality for Cognitive Architectures
Ruchira Dhar, Anders Søgaard
Accepted at LLMs & Cognition Workshop @ International Conference on Machine Learning (ICML), 2024

Preprints

Evaluation Revisited: A Taxonomy of Evaluation Concerns in Natural Language Processing
Ruchira Dhar, Anders Søgaard