2.1k citations · 2.1k across the 19 of their papers we have counts for
19 papers
Analyzing and Mitigating Cross-Lingual Degradation in Multilingual Medical VQA
Jingbo Wang, Sendong Zhao, Haochun Wang +2
Medical visual question answering (VQA) is a crucial task in clinical AI, yet its evaluation has so far centered almost exclusively on English, limiting its relevance to linguistic…
Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents
Ting Liu
Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, a skill often needs to expr…
Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection
Haochun Wang, Chaofen Yang, Jiatong Liu +5
In-context learning (ICL) is highly sensitive to which demonstrations appear in the prompt, but selecting them is expensive because the space of possible demonstration contexts and…
Orchestrating Intelligence: Confidence-Aware Routing for Efficient Multi-Agent Collaboration across Multi-Scale Models
Jingbo Wang, Sendong Zhao, Jiatong Liu +4
While multi-agent systems (MAS) have demonstrated superior performance over single-agent approaches in complex reasoning tasks, they often suffer from significant computational ine…
Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing
Zewen Qiang, Sendong Zhao, Haochun Wang +2
Large language models (LLMs) have demonstrated strong performance on a variety of natural language processing (NLP) tasks. However, they often struggle with long-text sequences due…
Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration
Jingbo Wang, Sendong Zhao, Haochun Wang +2
The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse agents to integrate unique experti…
MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security
Yanrui Du, Fenglei Fan, Sendong Zhao +3
As Large Language Models (LLMs) increasingly permeate human life, their security has emerged as a critical concern, particularly their ability to maintain harmless responses to mal…
Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint
Yanrui Du, Fenglei Fan, Sendong Zhao +6
Instruction Fine-Tuning (IFT) has been widely adopted as an effective post-training strategy to enhance various abilities of Large Language Models (LLMs). However, prior studies ha…
Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems
Haochun Wang, Sendong Zhao, Jingbo Wang +3
Multi-agent collaboration has emerged as a pivotal paradigm for addressing complex, distributed tasks in large language model (LLM)-driven applications. While prior research has fo…
Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning
Yanrui Du, Sendong Zhao, Jiawei Cao +6
Instruction fine-tuning has emerged as a critical technique for customizing Large Language Models (LLMs) to specific applications. However, recent studies have highlighted signific…
MolFusion: Multimodal Fusion Learning for Molecular Representations via Multi-granularity Views
Muzhen Cai, Sendong Zhao, Haochun Wang +4
Artificial Intelligence predicts drug properties by encoding drug molecules, aiding in the rapid screening of candidates. Different molecular representations, such as SMILES and mo…
AS-ES Learning: Towards Efficient CoT Learning in Small Models
Nuwa Xi, Yuhan Chen, Sendong Zhao +3
Chain-of-Thought (CoT) serves as a critical emerging ability in LLMs, especially when it comes to logical reasoning. Attempts have been made to induce such ability in small models…
LLMs May Perform MCQA by Selecting the Least Incorrect Option
Haochun Wang, Sendong Zhao, Zewen Qiang +3
In the field of NLP, Large Language Models (LLMs) have markedly enhanced performance across a variety of tasks. However, the comprehensive evaluation of LLMs remains an inevitable…
Beyond Direct Diagnosis: LLM-based Multi-Specialist Agent Consultation for Automatic Diagnosis
Haochun Wang, Sendong Zhao, Zewen Qiang +3
Automatic diagnosis is a significant application of AI in healthcare, where diagnoses are generated based on the symptom description of patients. Previous works have approached thi…
Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications
Zhangyin Feng, Weitao Ma, Weijiang Yu +7
Large language models (LLMs) exhibit superior performance on various natural language tasks, but they are susceptible to issues stemming from outdated data and domain-specific limi…
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
Lei Huang, Weijiang Yu, Weitao Ma +8
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Never…
Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese
Haochun Wang, Sendong Zhao, Zewen Qiang +9
Large Language Models (LLMs) have demonstrated remarkable success in diverse natural language processing (NLP) tasks in general domains. However, LLMs sometimes generate responses…
Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future
Zheng Chu, Jingchang Chen, Qianglong Chen +7
Reasoning, a fundamental cognitive process integral to human intelligence, has garnered substantial interest within artificial intelligence. Notably, recent studies have revealed t…
Manifold-based Verbalizer Space Re-embedding for Tuning-free Prompt-based Classification
Haochun Wang, Sendong Zhao, Chi Liu +4
Prompt-based classification adapts tasks to a cloze question format utilizing the [MASK] token and the filled tokens are then mapped to labels through pre-defined verbalizers. Rece…