Papers by Wenhui Zhu
Distilled Dual-Encoder Model for Vision-Language Understanding (2022.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that the proposed cross-modal attention distillation is crucial to the success of our framework. |
| Approach: | They propose a framework that distills knowledge of fusion-encoder teacher into dual-encoding student model. |
| Outcome: | The proposed model is competitive with the fusion-encoder teacher model in performance, but suffers from a lack of deep cross-modal interactions. |
Learning to Ask Unanswerable Questions for Machine Reading Comprehension (P19-1)
Copied to clipboard
| Challenge: | Existing models for extractive reading comprehension are not good at deciding whether no answer is presented in the context. |
| Approach: | They propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question paired with its corresponding paragraph that contains the answer. |
| Outcome: | The proposed model performs better on the SQuAD 2.0 dataset than the baseline model and the BERT-large model. |
AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives (2026.findings-acl)
Copied to clipboard
Yanxi Chen, Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Xin Li, Peijie Qiu, Hao Wang, Xuanzhao Dong, Yujian Xiong, Anderson Schneider, Yuriy Nevmyvaka, Yalin Wang
| Challenge: | Large Audio-Language Models suffer from hallucinations, e.g., generating text not grounded in the audio input. |
| Approach: | They propose a framework to address hallucination problems in large audio-language models . they use a preference dataset to test the model's accuracy . |
| Outcome: | The proposed model outperforms the latest SOTA methods in terms of performance and generalization. |
DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning (2026.findings-acl)
Copied to clipboard
Xiwen Chen, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hao Wang, Haiyu Wu, Huayu Li, Aris Sotiras, Yalin Wang, Abolfazl Razi
| Challenge: | Existing methods for group-relative policy optimization rely on scalar correctness rewards that are often non-injective with respect to semantic content. |
| Approach: | They propose a framework that calibrates the reward signal using the semantic density of sampled groups. |
| Outcome: | The proposed framework outperforms strong baselines on five math benchmarks with 7,000 samples and 55 cost. |