Knowledge Graph-Enhanced Large Language Models via Path Selection

H Liu, S Wang, Y Zhu, Y Dong, J Li - arxiv preprint arxiv:2406.13862, 2024‏ - arxiv.org
Large Language Models (LLMs) have shown unprecedented performance in various real-
world applications. However, they are known to generate factually inaccurate outputs, aka …

From instance to metric calibration: A unified framework for open-world few-shot learning

Y An, H Xue, X Zhao, J Wang - IEEE Transactions on Pattern …, 2023‏ - ieeexplore.ieee.org
Robust few-shot learning (RFSL), which aims to address noisy labels in few-shot learning,
has recently gained considerable attention. Existing RFSL methods are based on the …

Noise-robust fine-tuning of pretrained language models via external guidance

S Wang, Z Tan, R Guo, J Li - arxiv preprint arxiv:2311.01108, 2023‏ - arxiv.org
Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language
Models (PLMs) have achieved substantial advancements in the field of natural language …

Understanding user intent modeling for conversational recommender systems: a systematic literature review

S Farshidi, K Rezaee, S Mazaheri, AH Rahimi… - User Modeling and User …, 2024‏ - Springer
User intent modeling in natural language processing deciphers user requests to allow for
personalized responses. The substantial volume of research (exceeding 13,000 …

Joint agricultural intent detection and slot filling based on enhanced heterogeneous attention mechanism

X Hao, L Wang, H Zhu, X Guo - Computers and Electronics in Agriculture, 2023‏ - Elsevier
Agricultural diseases and pests are important factors restricting global food production. The
knowledge-based question-answering (Q&A) system opens a new avenue for pest and …

An intent taxonomy of legal case retrieval

Y Shao, H Li, Y Wu, Y Liu, Q Ai, J Mao, Y Ma… - ACM Transactions on …, 2023‏ - dl.acm.org
Legal case retrieval is a special Information Retrieval (IR) task focusing on legal case
documents. Depending on the downstream tasks of the retrieved case documents, users' …

APPN: An Attention-based Pseudo-label Propagation Network for few-shot learning with noisy labels

J Chen, S Deng, D Teng, D Chen, T Jia, H Wang - Neurocomputing, 2024‏ - Elsevier
Few-shot learning has garnered significant attention in deep learning as an effective
approach for addressing the issue of data scarcity. Conventionally, training datasets in few …

Warming Up Cold-Start CTR Prediction by Learning Item-Specific Feature Interactions

Y Wang, H Piao, D Dong, Q Yao, J Zhou - Proceedings of the 30th ACM …, 2024‏ - dl.acm.org
In recommendation systems, new items are continuously introduced, initially lacking
interaction records but gradually accumulating them over time. Accurately predicting the …

Meta-learning in healthcare: A survey

A Rafiei, R Moore, S Jahromi, F Hajati… - SN Computer …, 2024‏ - Springer
As a subset of machine learning, meta-learning, or learning to learn, aims at improving the
model's capabilities by employing prior knowledge and experience. A meta-learning …

Optimizing question answering systems in education: addressing domain-specific challenges

BP Swathi, M Geetha, G Attigeri, MV Suhas… - IEEE …, 2024‏ - ieeexplore.ieee.org
Question Answering (QA) systems are increasingly essential in educational institutions,
enhancing both learning and administrative processes by providing quick and accurate …