AI hallucinations: a misnomer worth clarifying
As large language models continue to advance in Artificial Intelligence (AI), text generation
systems have been shown to suffer from a problematic phenomenon often termed as" …
systems have been shown to suffer from a problematic phenomenon often termed as" …
[HTML][HTML] A survey of large language models for healthcare: from data, technology, and applications to accountability and ethics
The utilization of large language models (LLMs) for Healthcare has generated both
excitement and concern due to their ability to effectively respond to free-text queries with …
excitement and concern due to their ability to effectively respond to free-text queries with …
Seven pillars for the future of artificial intelligence
In recent years, artificial intelligence (AI) research has showcased tremendous potential to
positively impact humanity and society. Although AI frequently outperforms humans in tasks …
positively impact humanity and society. Although AI frequently outperforms humans in tasks …
An Overview of Text-based Person Search: Recent Advances and Future Directions
Due to the practical significance in smart video surveillance systems, Text-Based Person
Search (TBPS) has been one of the research hotspots recently, which refers to searching for …
Search (TBPS) has been one of the research hotspots recently, which refers to searching for …
Explainable natural language processing for corporate sustainability analysis
Sustainability commonly refers to entities, such as individuals, companies, and institutions,
having a non-detrimental (or even positive) impact on the environment, society, and the …
having a non-detrimental (or even positive) impact on the environment, society, and the …
Fusing pairwise modalities for emotion recognition in conversations
Multimodal fusion has the potential to significantly enhance model performance in the
domain of Emotion Recognition in Conversations (ERC) by efficiently integrating information …
domain of Emotion Recognition in Conversations (ERC) by efficiently integrating information …
Sarcasm driven by sentiment: A sentiment-aware hierarchical fusion network for multimodal sarcasm detection
Sarcasm is a form of sentiment expression that highlights the disparity between a person's
true intentions and the content they explicitly present. With the exponential increase in …
true intentions and the content they explicitly present. With the exponential increase in …
HiNER: Hierarchical feature fusion for Chinese named entity recognition
S Hou, Y Qian, J Chen, J Zhao, H Lv, J Zhang, H Leng… - Neurocomputing, 2025 - Elsevier
Abstract Named Entity Recognition (NER) aims to extract structured entity information from
unstructured textual data by identifying entity boundaries and categories. Chinese NER is …
unstructured textual data by identifying entity boundaries and categories. Chinese NER is …
Prompt Learning for Multimodal Intent Recognition with Modal Alignment Perception
Y Chen, W Zhu, W Yu, H Xue, H Fu, J Lin… - Cognitive Computation, 2024 - Springer
Multimodal intent recognition analysis is a crucial task in understanding user intent through
speech, body movements, tone, and other modalities in real-world multimodal environments …
speech, body movements, tone, and other modalities in real-world multimodal environments …
MORTAR: Metamorphic Multi-turn Testing for LLM-based Dialogue Systems
G Guo, A Aleti, N Neelofar… - arxiv preprint arxiv …, 2024 - arxiv.org
With the widespread application of LLM-based dialogue systems in daily life, quality
assurance has become more important than ever. Recent research has successfully …
assurance has become more important than ever. Recent research has successfully …