Papers by Yayue Deng
MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation approaches focus on mLLMs’ detection accuracy for binary classification tasks, which often fail to reflect the in-depth interpretive nuance of harmfulness across diverse contexts. |
| Approach: | They propose an agent-based arena-style evaluation framework that provides context-aware and unbiased assessment for mLLMs’ understanding of multimodal harmfulness. |
| Outcome: | The proposed framework reduces evaluation biases of judge agents and provides unbiased comparisons of mLLMs’ abilities to interpret multimodal harmfulness. |
UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for speech generation rely on subjective, expensive judgments . Existing models only cover a narrow set of scenarios and only provide limited coverage . |
| Approach: | They propose a unified speech reward model that can support multi-dimensional, interpretable reward signals with reliable reasoning. |
| Outcome: | The proposed model can support multi-dimensional, interpretable reward signals with reliable reasoning. |