Daisuke OBA

✈️ Off to Zhuhai for #AACL2026! 🚨 We are hiring! I’m looking for NLP talent at all levels: 🏛️ @LivUniCS (PhD students to Full Prof in AI) 📦 Amazon (Applied Scientists) My DMs are open—let's catch up on roles or research! Catch our work this week 👇 🗓️ Nov 7 | 10:30am (Interpretability) Oral: Decoupling Internal Representational Changes & Causal Importance in Fine-Tuned LLMs 🔗 aclanthology.org/2026.aacl-l… w/ @prochetasen @li_lingfang Subham Das 🗓️ Nov 8 | 10:30am (Semantics) Oral: WiC is not WSD: A Study on LLMs & Lexical Ambiguity Resolution 🔗 aclanthology.org/2026.aacl-l… w/ @jodieyzhou Kiamehr Rezaee @tpilehvar @CamachoCollados 🗓️ Nov 10 | 2:00pm Tutorial: Diffusion Language Models 🔗 dllm-aacl.github.io/ w/ @dai0NLP See you there! @aaclmeeting #aacl2026 #LiverpoolNLP @AmazonScience

Thrilled to announce that we have two papers and a tutorial accepted to AACL-IJCNLP. 🎉 1. Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models (with Lingfang Li, Procheta Sen, and Shubham Das) We investigated how fine-tuning fundamentally alters internal representation (like attention patterns and layer-wise activations) inside LLMs and discovered that components most causally important to a task's performance are actually concentrated within specific layers. Interestingly, the distribution of these causally important components is largely uncorrelated with the layers undergoing the most substantial representational changes during fine-tuning. If you are interested in how fine-tuning affects a model internally LLMs please get in touch. P 2, WiC is Not WSD: A Study on LLMs and Lexical Ambiguity Resolution (with @jodieyzhou , Kiamehr Rezaee, Mohammad Taher Pilehvar, and @CamachoCollados ) We explored why Word-in-Context (WiC) tasks remain so challenging for LLMs compared to traditional Word Sense Disambiguation (WSD). The difficulty isn't just about comparing two contextual uses of a word, but rather the lack of an explicit sense inventory that specifies the required level of semantic granularity. Providing candidate senses—similar to what is done in traditional WSD—improves WiC performance across all settings by helping models make more consistent judgments. Our human evaluation showed that many apparent LLM errors aren't simple failures of lexical understanding. Instead, LLMs tend to "overthink" and apply overly fine-grained sense distinctions compared to human annotators. 3. I will be giving a tutorial on Diffusion Language Models with @dai0NLP at AACL as well Preprints for both papers will be available soon. Congratulations to my collaborators/students #aacl26 #NLProc #LiverpoolNLP

Excited to give an invited talk at the @AIChemyHub "Transferable Opportunities for AI in Materials Chemistry" workshop in Liverpool on Sept 8! 🧬🗣️ Language and chemistry have striking parallels: words/grammar shape a sentence just like atoms/bonds shape a material. Because of this, NLP tools like Transformers and GNNs are unlocking new possibilities in materials science. I’ll be presenting "Mapping the Landscape of Foundation Models for Material Representation and Discovery," sharing how our latest #LiverpoolNLP research on mapping sentence encoders can be used to map material spaces and discover novel materials. 📅 Event info: aichemy.ac.uk/event/transfer… 📖 Read about our encoder mapping work: blog.danushka.net/posts/2026… #AI #NLP #MaterialScience #MachineLearning

We have two papers accepted to EMNLP 2026🎊 - Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space (main) Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka @verypluming - DyMT-ESB: Dynamic Multi-Turn Evaluation of Social Bias in User-LLM Interactions (Findings) Rem Hida, Masahiro Kaneko, Daisuke Oba, Danushka Bollegala, Naoaki Okazaki @rem_h4_ @MasahiroKaneko_ @dai0NLP Congrats to all my collaborators! #LiverpoolNLP