Lei Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Lei Huang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Bing Qin
Harbin Institute of Technology, Harbin, China
2 shared publications - Weitao Ma
Harbin Institute of Technology, Harbin, China
2 shared publications - Xiaocheng Feng
Faculty of Computing, Harbin Institute of Technology, Harbin, China
2 shared publications - Haotian Wang
Harbin Institute of Technology, Harbin, China
1 shared publication Leo Shen
Joint Lab with Wuhu Token for Graphene Electrical Materials and Application, Department of Physics, Shanghai Normal University, Guilin Road 100, Shanghai 200234, People's Republic of China
1 shared publication- Panpan Li
College of Materials Science and Engineering Sichuan University Chengdu China
1 shared publication
Latest Publications
- 29 August 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
Dynamic adaptive ensemble decoding under uncertainty for large language models
- 29 August 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
Dynamic adaptive ensemble decoding under uncertainty for large language models
- Top Cited PapersOpen Access
- 24 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (2) , 1-55
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Nevertheless, LLMs are prone to hallucination, generating plausible yet nonfactual content. This phenomenon raises significant concerns over the reliability of LLMs in real-world information retrieval (IR) systems and has attracted intensive research to detect and mitigate such hallucinations. Given the open-ended general-purpose attributes inherent to LLMs, LLM hallucinations present distinct challenges that diverge from prior task-specific models. This divergence highlights the urgency for a nuanced understanding and comprehensive overview of recent advances in LLM hallucinations. In this survey, we begin with an innovative taxonomy of hallucination in the era of LLM and then delve into the factors contributing to hallucinations. Subsequently, we present a thorough overview of hallucination detection methods and benchmarks. Our discussion then transfers to representative methodologies for mitigating LLM hallucinations. Additionally, we delve into the current limitations faced by retrieval-augmented LLMs in combating hallucinations, offering insights for developing more robust IR systems. Finally, we highlight the promising research directions on LLM hallucinations, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.
- 24 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (2) , 1-55
Top Cited PapersOpen AccessA Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Nevertheless, LLMs are prone to hallucination, generating plausible yet nonfactual content. This phenomenon raises significant concerns over the reliability of LLMs in real-world information retrieval (IR) systems and has attracted intensive research to detect and mitigate such hallucinations. Given the open-ended general-purpose attributes inherent to LLMs, LLM hallucinations present distinct challenges that diverge from prior task-specific models. This divergence highlights the urgency for a nuanced understanding and comprehensive overview of recent advances in LLM hallucinations. In this survey, we begin with an innovative taxonomy of hallucination in the era of LLM and then delve into the factors contributing to hallucinations. Subsequently, we present a thorough overview of hallucination detection methods and benchmarks. Our discussion then transfers to representative methodologies for mitigating LLM hallucinations. Additionally, we delve into the current limitations faced by retrieval-augmented LLMs in combating hallucinations, offering insights for developing more robust IR systems. Finally, we highlight the promising research directions on LLM hallucinations, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.
- 9 January 2014
- Published by IOP Publishing in Nanotechnology
- Vol. 25 (5) , 055603
Printable temperature-responsive hybrid hydrogels with photoluminescent carbon nanodots
Smart ink-like hybrid hydrogels that simultaneously possess semi-interpenetrating network structure, strong photoluminescence and temperature sensitivity are successfully fabricated based on the crosslink of poly(acrylamide) (PAAm) in the presence of poly(N-isopropylacrylamide) (PNIPAM) and carbon nanodots (CNDs) at room temperature. The resulting hybrid hydrogels were highly photoluminescent. The photoluminescence was sensitive to external temperature stimuli and reversible. Moreover, the hybrid hydrogels were applied as fluorescent inks for patterning using gravure printing, which may open a door towards developing smart CND based thermosensitive photoluminescent markers and sensors.
- 9 January 2014
- Published by IOP Publishing in Nanotechnology
- Vol. 25 (5) , 055603
Printable temperature-responsive hybrid hydrogels with photoluminescent carbon nanodots
Smart ink-like hybrid hydrogels that simultaneously possess semi-interpenetrating network structure, strong photoluminescence and temperature sensitivity are successfully fabricated based on the crosslink of poly(acrylamide) (PAAm) in the presence of poly(N-isopropylacrylamide) (PNIPAM) and carbon nanodots (CNDs) at room temperature. The resulting hybrid hydrogels were highly photoluminescent. The photoluminescence was sensitive to external temperature stimuli and reversible. Moreover, the hybrid hydrogels were applied as fluorescent inks for patterning using gravure printing, which may open a door towards developing smart CND based thermosensitive photoluminescent markers and sensors.