Papers by Sadaf Ghaffari
Large Language Models Are Challenged by Habitat-Centered Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing text-only and multimodal LLMs can reason about object habitats and affordances, but there appears to be a consistent low upper bound on habitat-centered reasoning performance. |
| Approach: | They evaluate 16 text-only and multimodal LLMs on a curated multimodal dataset of questions about object habitats and affordances . |
| Outcome: | The proposed model is based on 16 text-only and multimodal LLMs on a dataset of questions about object habitats and affordances. |