Papers by Deval Mehta
WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing MCoT methods focus on inter-object reasoning, overlooking intra-object understanding crucial for image classification. |
| Approach: | They propose a Weak-supervision-guided Step-by-step Explanation method that reformulates MCoTs under weak supervision into concise, interpretable reasoning chains. |
| Outcome: | The proposed method improves interpretability by 37% and improves classification accuracy. |
Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models (2025.acl-long)
Copied to clipboard
| Challenge: | Concept Bottleneck Models (CBMs) map visual representations to a set of humanunderstandable textual concepts, which are then interpreted by a linear combination of these concept scores. |
| Approach: | They propose a dynamic, agent-based approach that adjusts the concept bank in response to environmental feedback, optimizing the number of concepts for sufficiency yet concise coverage. |
| Outcome: | The proposed model improves classification accuracy by 6% and interpretability assessments by 30%. |