
Linguistic Principles for Foundation Models — the full-day programme of the LP4FM workshop, including the invited talks, the contributed orals and the poster session.
All times are Sydney local time (AEDT, UTC+11). Oral presentations are 6 minutes each, including Q&A.
| Time | Speaker | Topic |
|---|---|---|
| 09:00–09:10 | Organizers | Opening Remarks |
| 09:10–09:40 | Wray Buntine | Linguistic and Interpretative Capabilities of Foundation Models for Language |
| 09:40–10:10 | Cécile Paris | Question Answering Fit for Purpose: A Perspective from Natural Language Processing and User Modeling |
| 10:10–10:40 | Eduard Hovy | The Structure of Semantic Representation in Embedding Space |
| Contributed Orals I · 6 minutes each, including Q&A | ||
| 10:40–10:46 | Emanuele Sansone | Can AI Understand the Language of Origami? |
| 10:46–10:52 | Nicholas Runcie | Talk Like a Molecular Graph: Chemical Representations for Large Language Models |
| 10:52–10:58 | Jindong Wang | Beyond Structural Unification: A Perspective and Roadmap on Unified Multimodal Models |
| 10:58–11:04 | Kaibang Zhang | Same Answer, Different Path: Measuring Prompt Sensitivity Beyond Task Outcomes in Small Language Models |
| 11:04–11:10 | Tim Tomov | What Is a Clarification? Estimating Model-Dependent Input Ambiguity |
| 11:10–11:16 | Han Zhang | Adaptive Content-Contrastive Decoding for Representation-Robust Tabular Reasoning |
| 11:16–11:36 | — | Coffee Break |
| Contributed Orals II · 6 minutes each, including Q&A | ||
| 11:36–11:42 | Yan Liu | Triplet-Aware Sparse Higher-Order Attention for Natural Language Understanding |
| 11:42–11:48 | Kai Han | Where Natural Language Ends in Agents: Executable Skill Composition with MetaSkill |
| 11:48–11:54 | Chaoyang Zhou | Intra-Trajectory Consistency for Reward Modeling |
| 11:54–12:00 | Daniel Yoo | The Assistant Persona Differs Across Languages in Activation Space |
| 12:00–12:06 | Benedict Tessler | Model Hypnosis: Strong control of AI via additive subliminal effects |
| 12:06–13:00 | — | Lunch Break |
| 13:00–13:40 | Roger Levy Online | Linguistic structure, probability, and language processing in humans and large language models |
| 13:40–14:10 | Jey Han Lau | How linguistic relationships shape representation |
| 14:10–14:40 | Tal Linzen | Less Superhuman Language Models |
| 14:40–15:10 | Usman Naseem | Mechanistic-Driven AI Safety and Alignment |
| 15:10–15:40 | Reza Haffari | What Should an Instruction Make Explicit? Language and Planning in Foundation Models |
| 15:40–16:00 | — | Break |
| 16:00–17:00 | — | Poster Session & Coffee Break |
| 17:00–17:10 | Organizers | Closing Remarks |
The programme is subject to change.
We are excited to welcome leading researchers from linguistics, cognitive science, natural language processing, and machine learning.







