Yikun Han

Mr. Yikun Han

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 March 2025
Verified
Conference Paper
Open access
YTYijun Tian
Yijun Tian
YHYikun Han
Yikun Han
XCXiusi Chen
Xiusi Chen
WWWei Wang
Wei Wang
Nitesh ChawlaNitesh Chawla
Nitesh Chawla
Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation stands out due to its outstanding efficiency and generalization. However, existing methods suffer from several drawbacks, including limited knowledge diversity and the lack of rich contextual information. To solve the problems and facilitate the learning of compact language models, we propose TinyLLM, a new knowledge distillation paradigm to learn a small student LLM from multiple large teacher LLMs. In particular, we encourage the student LLM to not only generate the correct answers but also understand the rationales behind these answers. Given that different LLMs possess diverse reasoning skills, we guide the student model to assimilate knowledge from various teacher LLMs. We further introduce an in-context example generator and a teacher-forcing Chain-of-Thought strategy to ensure that the rationales are accurate and grounded in contextually appropriate scenarios. Extensive experiments on six datasets across two reasoning tasks demonstrate the superiority of our method. Results show that TinyLLM can outperform large teacher LLMs significantly, despite a considerably smaller model size. The source code is available at: https://github.com/YikunHan42/TinyLLM.

24 January 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
CLChunjiang Liu
Chunjiang Liu
YHYikun Han
Yikun Han
HXHaiyun Xu
Haiyun Xu
SYShihan Yang
Shihan Yang
KWKaidi Wang
Kaidi Wang
YSYongye Su
Yongye Su
This study presents a novel approach that synergizes community detection algorithms with various Graph Neural Network (GNN) models to bolster link prediction in scientific literature networks. By integrating the Louvain community detection algorithm into our GNN frameworks, we consistently enhanced the performance across all models tested. For example, integrating the Louvain model with the GAT model resulted in an AUC score increase from 0.777 to 0.823, exemplifying the typical improvements observed. Similar gains were noted when the Louvain model was paired with other GNN architectures, confirming the robustness and effectiveness of incorporating community-level insights. This consistent increase in performance—reflected in our extensive experimentation on bipartite graphs of scientific collaborations and citations—highlights the synergistic potential of combining community detection with GNNs to overcome common link prediction challenges such as scalability and resolution limits. Our findings advocate for the integration of community structures as a significant step forward in the predictive accuracy of network science models, offering a comprehensive understanding of scientific collaboration patterns through the lens of advanced machine learning techniques.

18 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
YHYikun Han
Yikun Han
CLChunjiang Liu
Chunjiang Liu
Pengfei WangPengfei Wang
Pengfei Wang
A vector database is used to store high-dimensional data that cannot be characterized by traditional DBMS. Although there are not many articles describing existing or introducing new vector database architectures, the approximate nearest neighbor search problem behind vector databases has been studied for a long time, and considerable related algorithmic articles can be found in the literature. This article attempts to comprehensively review relevant algorithms to provide a general understanding of this booming research area. The basis of our framework categorises these studies by the approach of solving ANNS problem, respectively hash-based, tree-based, graph-based and quantization-based approaches. Then we present an overview of existing challenges for vector databases. Lastly, we sketch how vector databases can be combined with large language models and provide new possibilities.

9 April 2024 in arXiv
Verified
Preprint
Open access
PDF file
KWKaipeng Wang
Kaipeng Wang
ZJZhi Jing
Zhi Jing
YSYongye Su
Yongye Su
YHYikun Han
Yikun Han
This paper delves into enhancing the classification performance on the GoEmotions dataset, a large, manually annotated dataset for emotion detection in text. The primary goal of this paper is to address the challenges of detecting subtle emotions in text, a complex issue in Natural Language Processing (NLP) with significant practical applications. The findings offer valuable insights into addressing the challenges of emotion detection in text and suggest directions for future research, including the potential for a survey paper that synthesizes methods and performances across various datasets in this domain.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
KCKyle Cox
Kyle Cox
JXJiawei Xu
Jiawei Xu
YHYikun Han
Yikun Han
RXRong Xu
Rong Xu
TLTianhao Li
Tianhao Li
YDYing Ding
Ying Ding
An interesting behavior in large language models (LLMs) is prompt sensitivity. When provided with different but semantically equivalent versions of the same prompt, models may produce very different distributions of answers. This suggests that the uncertainty reflected in a model's output distribution for one prompt may not reflect the model's uncertainty about the meaning of the prompt. We model prompt sensitivity as a type of generalization error, and show that sampling across the semantic concept space with paraphrasing perturbations improves uncertainty calibration without compromising accuracy. Additionally, we introduce a new metric for uncertainty decomposition in black-box LLMs that improves upon entropy-based decomposition by modeling semantic continuities in natural language generation. We show that this decomposition metric can be used to quantify how much LLM uncertainty is attributed to prompt sensitivity. Our work introduces a new way to improve uncertainty calibration in prompt-sensitive language models, and provides evidence that some LLMs fail to exhibit consistent general reasoning about the meanings of their inputs.

4 August 2026 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
VSVahid Satarifard
Vahid Satarifard
LSLaura Sisson
Laura Sisson
YHYikun Han
Yikun Han
PIPedro Ilídio
Pedro Ilídio
MHMatej Hladiš
Matej Hladiš
AKAlexei Koulakov
Alexei Koulakov
A central goal in sensory science is to establish quantitative mappings between physical stimuli and perceptual experience. Although such mappings are well defined in vision and audition, they remain elusive in olfaction, particularly for complex odor mixtures. Here, we show that perceptual distances between odor mixtures can be predicted with high fidelity and are unexpectedly well captured by a compact semantic space derived from single-molecule representations. In the Dialogue for Reverse Engineering Assessment and Methods Olfactory Mixtures Prediction Challenge, we assembled a unified dataset of odor-mixture pairs, benchmarked predictions on a hidden test set of 46 pairs, and integrated the top-performing models into a postchallenge ensemble. This model outperformed existing state-of-the-art approaches on the hidden test set, reducing RMSE by about 33% to 0.08 and increasing Pearson correlation by 53% to 0.57, and maintained strong performance on an independent validation set of 50 newly designed mixture pairs. An ensemble, retaining only olfactory semantic features for each model included, further improved predictions, raising the Pearson correlation by 7% to 0.61 on the test set and by 15% to 0.54 on the validation set. Given that semantic features were extracted from pure molecules, it suggests that mixture perception may not require fundamentally different representational principles from single-molecule olfaction. Together, these results establish a reproducible quantitative framework for olfactory mixture perception and advance efforts to measure, model, and engineer smell.