Papers by Tong Mo

Improving Knowledge Graph Completion with Generative Hard Negative Mining (2023.findings-acl)

Copied to clipboard

Zile Qiao, Wei Ye, Dingyao Yu, Tong Mo, Weiping Li, Shikun Zhang

Challenge:	Existing methods for knowledge graph completion (KGC) use generative methods with a self-information-enhanced training strategy to generate high-quality negatives.
Approach:	They propose to leverage a sequence-to-sequence architecture to generate high-quality hard negatives from the same decoding distributions as the anchor.
Outcome:	The proposed method produces high-quality negatives with good hardness and diversity on three KGC benchmarks.

SGG-R 3: From Next-Token Prediction to End-to-End Unbiased Scene Graph Generation (2026.findings-acl)

Copied to clipboard

Jiaye Feng, Qixiang Yin, Yuankun Liu, Tong Mo, Weiping Li

Multimodality

Challenge:	Existing methods for scene graph generation lack task-specific structured reasoning and sparse, long-tailed relation distributions.
Approach:	They propose a structured reasoning framework that integrates task-specific Chain-of-Thought and reinforcement learning with group sequence policy optimization to achieve unbiased scene graph generation.
Outcome:	The proposed framework achieves superior performance on two benchmarks.

Enhancing Neural Models with Vulnerability via Adversarial Attack (2020.coling-main)

Copied to clipboard

Rong Zhang, Qifei Zhou, Bo An, Weiping Li, Tong Mo, Bo Wu

Robustness in NLP

Challenge:	Existing work on adversarial attack to improve performance of NLSM tasks has not been done.
Approach:	They propose a general two-stage training framework to enhance neural models with Vulnerability via adversarial attack.
Outcome:	The proposed framework improves neural models with Vulnerability via adversarial attack on NLSM datasets.

MuSe: Multi-Stage Graph Reasoning via Vision-Language Models (2026.acl-long)

Copied to clipboard

Guanyu Wang, Xu Chu, Zhijie Tan, Xinrong Chen, Tong Mo, Weiping Li

Multimodality

Challenge:	Graph Neural Networks (GNNs) and graph transformers are inadequate for tasks with limited generalization.
Approach:	They propose a multi-stage graph reasoning framework based on vision-language models that incrementally samples and visualizes task-relevant subgraphs.
Outcome:	The proposed framework outperforms existing benchmarks in Graph-related tasks.

Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization (2026.acl-long)

Copied to clipboard

Xu Chu, Guanyu Wang, Zhijie Tan, Xinrong Chen, Ziyu Li, Tong Mo, Weiping Li

Responsible & Trustworthy NLP

Challenge:	Recent studies attempt to obtain optimal or suboptimal arrangements based on statistical results or using dataset-based search, but these methods increase inference overhead while leaving the model’s inherent order bias unresolved.
Approach:	They propose Dual Group Advantage Optimization (DGAO) which aims to improve model accuracy and order stability simultaneously.
Outcome:	The proposed method improves model accuracy and order stability while penalizing order-sensitive or incorrect responses.

RADO: Reasoning Audit-Driven Optimization for Rigorous Reasoning in High-Stakes Domains (2026.acl-long)

Copied to clipboard

Zhijie Tan, Xu Chu, Guanyu Wang, Ziyu Li, Weiping Li, Tong Mo

Reasoning

Challenge:	Current reinforcement learning paradigms rely on outcome-based rewards, overlooking latent logical fallacies in intermediate steps.
Approach:	They propose a specialized audit model augmented with external tools to identify local logical ruptures and calibrate reward signals.
Outcome:	The proposed framework improves accuracy and logical rigor in high-stakes domains.

DESED: Dialogue-based Explanation for Sentence-level Event Detection (2022.coling-1)

Copied to clipboard

Yinyi Wei, Shuaipeng Liu, Jianwei Lv, Xiangyu Xi, Hailei Yan, Wei Ye, Tong Mo, Fan Yang, Guanglu Wan

Dialogue Systems & Conversational Agents

Challenge:	Existing methods for sentence-level event detection depend on manual annotations or domain expertise to design sophisticated templates and rules.
Approach:	They propose a dialogue-based explanation paradigm to enhance sentence semantics for event detection.
Outcome:	The proposed method can be applied to two event detection datasets.

Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains (2025.findings-acl)

Copied to clipboard

Xu Chu, Zhijie Tan, Hanlin Xue, Guanyu Wang, Tong Mo, Weiping Li

Responsible & Trustworthy NLP

Challenge:	Existing Large Language Models (LLMs) generate brief answers without reasoning processes and explanations.
Approach:	They propose supervised fine-tuning and tree search to enhance LLMs’ reasoning capabilities on domain tasks.
Outcome:	The proposed model improves on stock investment recommendation and legal reasoning QA tasks.

Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering over Knowledge Graphs (2022.coling-1)

Copied to clipboard

Zile Qiao, Wei Ye, Tong Zhang, Tong Mo, Weiping Li, Shikun Zhang

Structured Data in NLP

Challenge:	Existing approaches to answer natural language questions on knowledge graphs (KGQA) use large-scale entity-related text corpus or knowledge graph embeddings as auxiliary information to facilitate answer selection.
Approach:	They propose to integrate explicit textual information and implicit KG structural features of relation paths into a novel rotate-and-scale entity link prediction framework.
Outcome:	The proposed method is superior to existing methods on three KGQA datasets and shows that it can be used to identify answer entities.

Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling (2025.findings-naacl)

Copied to clipboard

Zile Qiao, Wei Ye, Yong Jiang, Tong Mo, Pengjun Xie, Weiping Li, Fei Huang, Shikun Zhang

Semantic Text Processing

Challenge:	Recent advances in large language models (LLMs) have significantly enhanced their performance in various natural language processing tasks.
Approach:	They propose a robust and pluggable knowledge rewriter that is optimized for LLM generation by supporting the model's supportiveness.
Outcome:	The proposed model can be used to rewrite knowledge in a supervised manner.

KiPT: Knowledge-injected Prompt Tuning for Event Detection (2022.coling-1)

Copied to clipboard

Haochen Li, Tong Mo, Hongcheng Fan, Jingkun Wang, Jiaxi Wang, Fuhao Zhang, Weiping Li

Low-Resource NLP

Challenge:	Existing prompt-based methods may suffer from low precision because they lack event-related semantic knowledge.
Approach:	They propose a Knowledge-injected Prompt Tuning model to improve prompt tuning . event detection aims to detect events from text by identifying and classifying event triggers .
Outcome:	The proposed model outperforms baseline models in few-shot scenarios.

GuiLoMo: Allocating Experts and Ranks for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors (2025.findings-emnlp)

Copied to clipboard

Xinrong Chen, Hengyuan Zhang, Yingmin Qiu, Xiao Liang, Ziyue Li, Guanyu Wang, Weiping Li, Tong Mo, Hayden Kwok-Hay So, Ngai Wong

Green & Sustainable NLP

Challenge:	Low-Rank Adaptation (LoRA) methods are efficient for a large language model with reduced computational costs.
Approach:	They propose a layer-wise expert numbers and ranks allocation strategy with GuidedSelection Vectors.
Outcome:	The proposed method achieves superior or comparable performance to all baselines on three backbone models.