Search Results for author:
Found 4 papers, 3 papers with code
GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models
Our evaluation reveals significant shortcomings in the language grounding and intuitive physics capabilities of these models.
On the Relationship between Skill Neurons and Robustness in Prompt Tuning
We show that prompts tuned for a specific task are transferable to tasks of the same type but are not very robust to adversarial data.
Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses
At the staggering pace with which the capabilities of large language models (LLMs) are increasing, creating future-proof evaluation sets to assess their understanding becomes more and more challenging.
Emergence of hierarchical reference systems in multi-agent communication
We develop a novel communication game, the hierarchical reference game, to study the emergence of such reference systems in artificial agents.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
