Papers by Jinhua Du
A Survey of Post-Training Scaling in Large Language Models (2025.acl-long)
Copied to clipboard
Hanyu Lai, Xiao Liu, Junjie Gao, Jiale Cheng, Zehan Qi, Yifan Xu, Shuntian Yao, Dan Zhang, Jinhua Du, Zhenyu Hou, Xin Lv, Minlie Huang, Yuxiao Dong, Jie Tang
| Challenge: | Large language models (LLMs) have demonstrated proficiency in understanding and generating human natural languages. |
| Approach: | They propose a framework for scaling large language models using supervised fine-tuning, RLxF and test-time compute methodologies. |
| Outcome: | The proposed model can be used to understand and generate human natural languages. |
EnigmaToM: Improve LLMs’ Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing ToM reasoning methods rely excessively on off-the-shelf LLMs, reducing their efficiency and limiting their applicability to high-order ToM. |
| Approach: | They propose a neuro-symbolic framework that integrates a Neural Knowledge Base of Entity States and knowledge injection to enhance ToM reasoning. |
| Outcome: | The proposed framework improves ToM reasoning on ToMi, HiToM, and FANToM benchmarks. |
From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities (2025.findings-acl)
Copied to clipboard
Shixin Jiang, Jiafeng Liang, Jiyuan Wang, Xuan Dong, Heng Chang, Weijiang Yu, Jinhua Du, Ming Liu, Bing Qin
| Challenge: | MLLMs are able to integrate multiple modalities into a single model to tackle complex tasks in real-world scenarios. |
| Approach: | They propose a comprehensive survey of Omni-MLLMs to address the challenges and opportunities of multimodal modeling. |
| Outcome: | The proposed model can integrate multiple modalities into a single model and provide novel perspectives. |
OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing N-ToM benchmarks lack ambiguous and artificial narratives, lack of personality traits and preferences, and limited diversity in the questions posed. |
| Approach: | They propose a benchmark to assess Neural Theory-of-Mind (N-ToM) with longer and clearer narrative stories, characters with explicit personality traits, actions triggered by character intentions, and questions designed to challenge LLMs’ abilities of modeling characters’ mental states. |
| Outcome: | The proposed test aims to assess the performance of LLMs in the physical and psychological worlds. |
Self-Attention Enhanced CNNs and Collaborative Curriculum Learning for Distantly Supervised Relation Extraction (D19-1)
Copied to clipboard
| Challenge: | Distantly Supervised Relation Extraction (DSRE) suffers from mislabelled data . human annotation on large datasets is costly and often impossible . |
| Approach: | They propose a model that employs a collaborative curriculum learning framework to reduce mislabelled data. |
| Outcome: | The proposed model outperforms baselines including state-of-the-art in terms of P@N and PR curve metrics on a widely-used public dataset. |
Pointing to Select: A Fast Pointer-LSTM for Long Text Classification (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to skip irrelevant words in text processing are slow and vanishing gradients can cause slow inference and a loss of coherence. |
| Approach: | They propose a pointer network-based LSTM framework which can change skip rates during inference. |
| Outcome: | The proposed model is 1.1x3.5x faster than the standard LSTM framework and more accurate than Leap-LSTM at high skip rates. |
NextGen AML: Distributed Deep Learning based Language Technologies to Augment Anti Money Laundering Investigation (P18-4)
Copied to clipboard
| Challenge: | Money laundering (AML) is the process of transferring criminal and illegal proceeds into ostensibly legitimate assets. |
| Approach: | They propose a framework that uses deep learning to augment AML monitoring and investigation . money laundering is the process of transferring criminal and illegal proceeds into ostensibly legitimate assets . |
| Outcome: | The proposed framework reduces time and cost by 30% compared to existing methods . money laundering is the world's third largest "industry" |
Generating Domain-Specific Knowledge Graphs from Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown impressive world knowledge across different benchmarks and domains but their knowledge is inconveniently scattered across their billions of parameters. |
| Approach: | They propose a prompt-based method to extract knowledge solely from LLMs’ parameters to construct domain-specific KGs by a schema-based process. |
| Outcome: | The proposed method generates large domain-specific KGs containing tens of thousands of entities and relations, and then evaluates against Wikidata, an open-source human-created KG. |
Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to label large-scale data are inadequate for distantly supervised relation extraction (DS-RE). |
| Approach: | They propose a multi-level structured (2-D matrix) self-attention mechanism for DS-RE using bidirectional recurrent neural networks. |
| Outcome: | The proposed framework significantly outperforms baselines on two publicly available DS-RE datasets in terms of PR curves, P@N and F1 measures. |