Papers by Guohui Li
GLAF: Global-to-Local Aggregation and Fission Network for Semantic Level Fact Verification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing fact verification models lack fine-grained reasoning over key entities . GLAF uses local fission reasoning to capture latent logical relations between clues . |
| Approach: | They propose a global-to-local fission and fissional network to capture latent logical relations hidden in multiple evidence clues. |
| Outcome: | The proposed network achieves state-of-the-art on a FEVER dataset with a 77.62% FEVER score. |
MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)
Copied to clipboard
Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang, Yongqian Wen, Yuanxing Zhang, Haoxuan Hu, Zhiyu Pan, Yibing Huang, Zhidong Gan, Yonghong Lin, An Ping, Shihao Li, Yanghai Wang, Tianhao Peng, Jiaheng Liu
| Challenge: | Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios. |
| Approach: | They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity. |
| Outcome: | The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues. |
UniTranSeR: A Unified Transformer Semantic Representation Framework for Multimodal Task-Oriented Dialog System (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies on multimodal task-oriented dialog systems follow the pipeline to learn intra-modal features separately and then conduct simple feature concatenation or attention-based feature fusion to generate responses. |
| Approach: | They propose a Unified Transformer Semantic Representation framework with feature alignment and intention reasoning for multimodal dialog systems that embed multimodal features into a unified Transformer semantic space to prompt inter-modal interactions. |
| Outcome: | The proposed framework significantly outperforms state-of-the-art approaches on the representative MMD dataset. |
Intention Reasoning Network for Multi-Domain End-to-end Task-Oriented Dialogue (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent years has witnessed the remarkable success in end-to-end task-oriented dialog system, especially when incorporating external knowledge information. |
| Approach: | They propose a mechanism to model deterministic entity knowledge by using an intention reasoning network to obtain intention-aware representations of conceptual tokens. |
| Outcome: | The proposed mechanism captures concept shifts and generates accurate responses on two representative multi-domain dialog datasets. |