2.1k citations · 2.1k across the 20 of their papers we have counts for
22 papers
VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning
Chenglin Li, Qianglong Chen, Feng Han +6
Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning over uniformly sampled frames,…
VideoPro: Adaptive Program Reasoning for Long Video Understanding
Chenglin Li, Feng Han, Yikun Wang +9
Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic r…
Iterative Zoom-In: Temporal Interval Exploration for Long Video Understanding
Chenglin Li, Qianglong Chen, fengtao +1
Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding tasks. However, they continue to struggle with long-form videos because of an ineffici…
VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models
Chenglin Li, Qianglong Chen, Zhi Li +2
Recent advancements in Large Video-Language Models (LVLMs) have led to promising results in multimodal video understanding. However, it remains unclear whether these models possess…
Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search
Chenglin Li, Qianglong Chen, Zhi Li +5
Instruction tuning is a crucial technique for aligning language models with humans' actual goals in the real world. Extensive research has highlighted the quality of instruction da…
Mixed Distillation Helps Smaller Language Model Better Reasoning
Chenglin Li, Qianglong Chen, Liangyue Li +4
While large language models (LLMs) have demonstrated exceptional performance in recent natural language processing (NLP) tasks, their deployment poses substantial challenges due to…
Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System
Haotian Wang, Xiyuan Du, Weijiang Yu +5
Multi-agent debate system (MAD) imitating the process of human discussion in pursuit of truth, aims to align the correct cognition of different agents for the optimal solution. It…
TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models
Zheng Chu, Jingchang Chen, Qianglong Chen +4
Grasping the concept of time is a fundamental facet of human cognition, indispensable for truly comprehending the intricacies of the world. Previous studies typically focus on spec…
Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications
Zhangyin Feng, Weitao Ma, Weijiang Yu +7
Large language models (LLMs) exhibit superior performance on various natural language tasks, but they are susceptible to issues stemming from outdated data and domain-specific limi…
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
Lei Huang, Weijiang Yu, Weitao Ma +8
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Never…
Large Language Models Are Also Good Prototypical Commonsense Reasoners
Chenin Li, Qianglong Chen, Yin Zhang +2
Commonsense reasoning is a pivotal skill for large language models, yet it presents persistent challenges in specific tasks requiring this competence. Traditional fine-tuning appro…
Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future
Zheng Chu, Jingchang Chen, Qianglong Chen +7
Reasoning, a fundamental cognitive process integral to human intelligence, has garnered substantial interest within artificial intelligence. Notably, recent studies have revealed t…
WYWEB: A NLP Evaluation Benchmark For Classical Chinese
Bo Zhou, Qianglong Chen, Tianyu Wang +2
To fully evaluate the overall performance of different NLP models in a given domain, many evaluation benchmarks are proposed, such as GLUE, SuperGLUE and CLUE. The fi eld of natura…
Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering
Qianglong Chen, Guohai Xu, Ming Yan +4
Existing knowledge-enhanced methods have achieved remarkable results in certain QA tasks via obtaining diverse knowledge from different knowledge bases. However, limited by the pro…
AMTSS: An Adaptive Multi-Teacher Single-Student Knowledge Distillation Framework For Multilingual Language Inference
Qianglong Chen, Feng Ji, Feng-Lin Li +4
Knowledge distillation is of key importance to launching multilingual pre-trained language models for real applications. To support cost-effective language inference in multilingua…
Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning
Wenjin Wang, Yunqing Hu, Qianglong Chen +1
Parameter regularization or allocation methods are effective in overcoming catastrophic forgetting in lifelong learning. However, they solve all tasks in a sequence uniformly and i…
ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding
Wenjin Wang, Zhengjie Huang, Bin Luo +8
Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approa…
DictBERT: Dictionary Description Knowledge Enhanced Language Model Pre-training via Contrastive Learning
Qianglong Chen, Feng-Lin Li, Guohai Xu +3
Although pre-trained language models (PLMs) have achieved state-of-the-art performance on various natural language processing (NLP) tasks, they are shown to be lacking in knowledge…
Rethinking the Value of Gazetteer in Chinese Named Entity Recognition
Qianglong Chen, Xiangji Zeng, Jiangang Zhu +4
Gazetteer is widely used in Chinese named entity recognition (NER) to enhance span boundary detection and type classification. However, to further understand the generalizability a…
Semantic Sentence Composition Reasoning for Multi-Hop Question Answering
Qianglong Chen
Due to the lack of insufficient data, existing multi-hop open domain question answering systems require to effectively find out relevant supporting facts according to each question…
K-AID: Enhancing Pre-trained Language Models with Domain Knowledge for Question Answering
Fu Sun, Feng-Lin Li, Ruize Wang +3
Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice…
Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources
Qianglong Chen, Feng Ji, Haiqing Chen +1
In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge. However, how to engage commonsense effectively in question answerin…