EurIPS 2025 Workshop MetaGenAI Submissions

Artificial Theory of Mind in Human-in-the-Loop
Sammie Katt, Samuel Kaski
- Published: 04 Nov 2025, Last Modified: 21 Nov 2025
- MetaGenAI2025 Oral
- Readers: Everyone
Query-Level Uncertainty in Large Language Models
Lihu Chen, Gerard de Melo, Fabian M. Suchanek, Gaël Varoquaux
- Published: 04 Nov 2025, Last Modified: 22 Nov 2025
- MetaGenAI2025 Oral
- Readers: Everyone
Multiple Token Divergence: Measuring and Steering In-Context Computation Density
Vincent Herrmann, Eric Alcaide, Michael Wand, Jürgen Schmidhuber
- Published: 04 Nov 2025, Last Modified: 13 Nov 2025
- MetaGenAI2025 Poster
- Readers: Everyone
Physics-Informed Metacognition: Improving LLMs Self-Knowledge via Physical Constraints
Mahule Roy, Subhas Roy
- Published: 04 Nov 2025, Last Modified: 16 Nov 2025
- MetaGenAI2025 Poster
- Readers: Everyone
Evaluating Long-Term Memory for Long-Context Question Answering
Alessandra Terranova, Alexandra Birch, Björn Ross
- Published: 04 Nov 2025, Last Modified: 22 Nov 2025
- MetaGenAI2025 Poster
- Readers: Everyone
A Pipeline for Assessing Metacognitive Reasoning in Energy-Based Transformers while Generating Code
Tailia Malloy, Prateek Kumar Rajput, Iyiola Emmanuel Olatunji, Jacques Klein, Tegawendé F. Bissyandé
- Published: 04 Nov 2025, Last Modified: 13 Nov 2025
- MetaGenAI2025 Poster
- Readers: Everyone
Strengthening LLM Identity Mitigates and Reverses Emergent Misalignment
Arush Tagade, Shaoheng Zhou, Shi Feng
- Published: 04 Nov 2025, Last Modified: 13 Nov 2025
- MetaGenAI2025 Poster
- Readers: Everyone
Awareness in LLMs Improves Through Collaboration
Lucia Passaro, SIMONE MARZEDDU, Andrea Cossu, Davide Bacciu
- Published: 04 Nov 2025, Last Modified: 21 Nov 2025
- MetaGenAI2025 Poster
- Readers: Everyone
AP-OOD: Attention Pooling for Out-of-Distribution Detection
Claus Hofmann, Christian Huber, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter, Werner Zellinger
- Published: 04 Nov 2025, Last Modified: 21 Nov 2025
- MetaGenAI2025 Poster
- Readers: Everyone