3 citations · 11 across the 16 of their papers we have counts for
18 papers
Beyond Explicit Intent: Discovering and Shaping Artistic Intent through Human-AI Co-Creation
Renye Yan, Jialun Zhong, Jikang Cheng +3
Generative AI is becoming an important medium for artistic creation, yet existing interactions often assume that creators can specify intentions in advance and accurately communica…
Are Benchmarks Reliable? Toward Structural Diagnosis via Item-Level Capability Boundaries
Haiquan Hu, Yuzhu Liang, Weicheng Tang +4
Evaluating large language models (LLMs) relies heavily on benchmark scores, yet aggregate metrics can obscure whether individual items serve their intended measurement purpose. BSD…
DySRec: Dynamic Context-Aware Psychometric Scale Recommendation via Multi-Agent Collaboration
Yanzeng Li, Xiaoning Cao, Jialun Zhong +5
Choosing suitable psychometric scales is an essential and difficult step in psychological consultation, which requires clinicians to integrate patient information, behaviors, and d…
Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph
Jianpeng Hu, Yanzeng Li, Jialun Zhong +2
The Retrieval-augmented generation (RAG) system based on Large language model (LLM) has made significant progress. It can effectively reduce factuality hallucinations, but faithful…
SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs
Hao Wang, Jialun Zhong, Changcheng Wang +5
Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual dependencies, and executing complex logical…
GAP: Graph-Assisted Prompts for Dialogue-based Medication Recommendation
Jialun Zhong, Yanzeng Li, Sen Hu +3
Medication recommendations have become an important task in the healthcare domain, especially in measuring the accuracy and safety of medical dialogue systems (MDS). Different from…
A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future
Jialun Zhong, Wei Shen, Yanzeng Li +7
Reward Model (RM) has demonstrated impressive potential for enhancing Large Language Models (LLM), as RM can serve as a proxy for human preferences, providing signals to guide LLMs…
Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking
Yanzeng Li, Yunfan Xiong, Jialun Zhong +3
The rise of Large Language Models (LLMs) has led to significant applications but also introduced serious security threats, particularly from jailbreak attacks that manipulate outpu…
DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure
Yunfan Xiong, Ruoyu Zhang, Yanzeng Li +2
While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly b…
MedDiT: A Knowledge-Controlled Diffusion Transformer Framework for Dynamic Medical Image Generation in Virtual Simulated Patient
Yanzeng Li, Cheng Zeng, Jinchao Zhang +2
Medical education relies heavily on Simulated Patients (SPs) to provide a safe environment for students to practice clinical skills, including medical image analysis. However, the…
MMPKUBase: A Comprehensive and High-quality Chinese Multi-modal Knowledge Graph
Xuan Yi, Yanzeng Li, Lei Zou
Multi-modal knowledge graphs have emerged as a powerful approach for information representation, combining data from different modalities such as text, images, and videos. While se…
LLMaAA: Making Large Language Models as Active Annotators
Ruoyu Zhang, Yanzeng Li, Yongliang Ma +2
Prevalent supervised learning methods in natural language processing (NLP) are notoriously data-hungry, which demand large amounts of high-quality annotated data. In practice, acqu…
Two is Better Than One: Answering Complex Questions by Multiple Knowledge Sources with Generalized Links
Minhao Zhang, Yongliang Ma, Yanzeng Li +3
Incorporating multiple knowledge sources is proven to be beneficial for answering complex factoid questions. To utilize multiple knowledge bases (KB), previous works merge all KBs…
ADMUS: A Progressive Question Answering Framework Adaptable to Multiple Knowledge Sources
Yirui Zhan, Yanzeng Li, Minhao Zhang +1
With the introduction of deep learning models, semantic parsingbased knowledge base question answering (KBQA) systems have achieved high performance in handling complex questions.…
VGStore: A Multimodal Extension to SPARQL for Querying RDF Scene Graph
Yanzeng Li, Zilong Zheng, Wenjuan Han +1
Semantic Web technology has successfully facilitated many RDF models with rich data representation methods. It also has the potential ability to represent and store multimodal know…
gBuilder: A Scalable Knowledge Graph Construction System for Unstructured Corpus
Yanzeng Li, Lei Zou
We design a user-friendly and scalable knowledge graph construction (KGC) system for extracting structured knowledge from the unstructured corpus. Different from existing KGC syste…
Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base
Minhao Zhang, Ruoyu Zhang, Yanzeng Li +1
Semantic parsing solves knowledge base (KB) question answering (KBQA) by composing a KB query, which generally involves node extraction (NE) and graph composition (GC) to detect an…
Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention
Yanzeng Li, Bowen Yu, Mengge Xue +1
Most Chinese pre-trained models take character as the basic unit and learn representation according to character's external contexts, ignoring the semantics expressed in the word,…