6 papers
Route-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs
Tien-Phat Nguyen, Truong Nguyen, Thanh-Thien Le +4
Large language models often apply complex reasoning indiscriminately, leading to overthinking on simple tasks and underthinking on harder ones. We present Route-and-Generate (Rouge…
Few-Shot, No Problem: Descriptive Continual Relation Extraction
Nguyen Xuan Thanh, Anh Duc Le, Quyen Tran +3
Few-shot Continual Relation Extraction is a crucial challenge for enabling AI systems to identify and adapt to evolving relationships in dynamic real-world domains. Traditional mem…
Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective
Minh Le, Tien Ngoc Luu, An Nguyen The +5
To address catastrophic forgetting in Continual Relation Extraction (CRE), many current approaches rely on memory buffers to rehearse previously learned knowledge while acquiring n…
Lifelong Event Detection via Optimal Transport
Viet Dao, Van-Cuong Pham, Quyen Tran +3
Continual Event Detection (CED) poses a formidable challenge due to the catastrophic forgetting phenomenon, where learning new tasks (with new coming event types) hampers performan…
ToVo: Toxicity Taxonomy via Voting
Tinh Son Luong, Thanh-Thien Le, Thang Viet Doan +3
Existing toxic detection models face significant limitations, such as lack of transparency, customization, and reproducibility. These challenges stem from the closed-source nature…
Realistic Evaluation of Toxicity in Large Language Models
Tinh Son Luong, Thanh-Thien Le, Linh Ngo Van +1
Large language models (LLMs) have become integral to our professional workflows and daily lives. Nevertheless, these machine companions of ours have a critical flaw: the huge amoun…