Papers by Mao Gu
Generating Fine Details of Entity Interactions (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing text-to-image models excel at generating high-quality object-centric images from instructions, but lack of data for complex interactions. |
| Approach: | They propose a multimodal Large Language Models-generated dataset to benchmark and enhance interaction-rich images. |
| Outcome: | The proposed approach improves image quality and automatic and human evaluations show improvements. |
Video Dialog via Progressive Inference and Cross-Transformer (D19-1)
Copied to clipboard
| Challenge: | Existing visual dialog methods use RNN to encode the dialog history as a vector representation . a new method for video dialog is proposed, which progressively updates query information based on dialog history and video content until the agent think the information is sufficient and unambiguous. |
| Approach: | They propose a method which progressively updates query information based on dialog history and video content until the agent thinks it is sufficient and unambiguous. |
| Outcome: | The proposed method can be used to infer video dialog answers on large-scale datasets. |
Bipartite Graph Pre-training for Unsupervised Extractive Summarization with Graph Convolutional Auto-Encoders (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to rank sentences using pre-trained embeddings create a gap due to different optimization objectives. |
| Approach: | They propose a pre-trained embedding process that optimizes informative sentences . they use sentence-word bipartite graphs to model intra-sentential distinctive features . |
| Outcome: | The proposed model outperforms heavy BERT- or RoBERTa-based sentence ranking methods by providing summary-worthy representations. |
Editing Conceptual Knowledge for Large Language Models (2024.findings-emnlp)
Copied to clipboard
Xiaohan Wang, Shengyu Mao, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang
| Challenge: | Existing knowledge editing methods can modify concept-level definitions, but they can distort instantial knowledge in LLMs, leading to poor performance. |
| Approach: | They construct a benchmark dataset ConceptEdit and establish new metrics for evaluation to investigate the editing capability of LLMs. |
| Outcome: | The proposed methods can modify concept definitions but can distort instantial knowledge in LLMs, leading to poor performance. |
BLADE: Benchmarking Language Model Agents for Data-Driven Science (2024.findings-emnlp)
Copied to clipboard
Ken Gu, Ruoxi Shang, Ruien Jiang, Keying Kuang, Richard-John Lin, Donghe Lyu, Yue Mao, Youran Pan, Teng Wu, Jiaqian Yu, Yikun Zhang, Tianmai Zhang, Lanyi Zhu, Mike Merrill, Jeffrey Heer, Tim Althoff
| Challenge: | Language model-based agents can be used to conduct and support data-driven science, but evaluating them on open-ended tasks is challenging due to multiple valid approaches, partially correct steps, and different ways to express the same decisions. |
| Approach: | They propose a benchmark to automatically evaluate agents’ multifaceted approaches to open-ended research questions. |
| Outcome: | BLADE evaluates agents’ multifaceted approaches to open-ended research questions using data from 12 datasets and research questions drawn from existing scientific literature. |
Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Walk-based models have shown their advantages in knowledge graph reasoning but are limited by their representations and generalizability. |
| Approach: | They propose a walk-based model that leverages high-quality rules generated by symbolic-based methods to provide reward supervision for walk- based agents. |
| Outcome: | Experiments on benchmark datasets show that RuleGuider improves the performance of walk-based models without losing interpretability. |
End-to-End Reinforcement Learning for Automatic Taxonomy Induction (P18-1)
Copied to clipboard
| Challenge: | Existing methods for automating taxonomy induction often divide the problem into two subtasks . a novel end-to-end reinforcement learning approach is proposed to improve the accuracy of such methods. |
| Approach: | They propose an end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on two public datasets of different domains. |
Improve Safety Training of Large Language Models with Safety-Critical Singular Vectors Localization (2025.acl-long)
Copied to clipboard
| Challenge: | Recent work on safety training with modules such as low-rank adaptation (LoRA) to resist jailbreaks shows promise, but these approaches can inadvertently degrade a model’s general utility. |
| Approach: | They propose a plug-and-play method that locates safety-critical singular vectors within the model's parameter space and a dynamic rank number determination strategy to reduce parameter overhead. |
| Outcome: | The proposed method mitigates the impact of safety training on model utility by explicitly locating and leveraging safety-critical singular vectors within the model’s parameter space. |
Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society (2026.acl-tutorials)
Copied to clipboard
Zheyuan Liu, Yixin Wan, Kai-Wei Chang, Meng Jiang, Jieyu Zhao, Nouha Dziri, Yuning Mao, Jia-Chen Gu, Jindong Gu
| Challenge: | This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods. |
| Approach: | This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods. |
| Outcome: | This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods . key motivations and failure modes, harmful generation and stereotype reinforcement, are addressed . core methods such as machine unlearning, knowledge editing, and inference-time interventions are also included . |
IAEval: A Comprehensive Evaluation of Instance Attribution on Natural Language Understanding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Instance attribution (IA) aims to identify the training instances leading to the prediction of a test example. |
| Approach: | They propose a systematic and comprehensive evaluation scheme covering four significant requirements: sufficiency, completeness, stability and plausibility. |
| Outcome: | The proposed evaluation scheme covers four significant requirements: sufficiency, completeness, stability and plausibility. |