| 2025 | EMNLP | Understanding and Improving Information Preservation in Prompt Compression for LLMs. | Weronika Lajewska, Momchil Hardalov, Laura Aina, Neha Anna John, Hang Su, Llus Mrquez |
| 2024 | ACL | Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators. | Mato Mahaut, Laura Aina, Paula Czarnowska, Momchil Hardalov, Thomas Mller, Llus Mrquez |
| 2022 | IJCNLP | Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks. | Laura Aina, Nikos Voskarides, Roi Blanco |
| 2021 | CoNLL | Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution. | Laura Aina, Xixian Liao, Gemma Boleda, Matthijs Westera |
| 2020 | CogSci | Modeling word interpretation with deep language models: The interaction between expectations and lexical information. | Laura Aina, Thomas Brochhagen, Gemma Boleda |
| 2019 | ACL | Putting Words in Context: LSTM Language Models and Lexical Ambiguity. | Laura Aina, Kristina Gulordava, Gemma Boleda |
| 2019 | NAACL | What do Entity-Centric Models Learn? Insights from Entity Linking in Multi-Party Dialogue. | Laura Aina, Carina Silberer, Ionut-Teodor Sorodoc, Matthijs Westera, Gemma Boleda |
| 2018 | EMNLP | How to represent a word and predict it, too: improving tied architectures for language modelling. | Kristina Gulordava, Laura Aina, Gemma Boleda |