97 citations · 146 across the 33 of their papers we have counts for
35 papers
Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded Inference
Danyang Zhao, Sendong Zhao, Yanrui Du +6
Reliable medical reasoning requires LLMs to dynamically access external biomedical evidence to improve factual trustworthiness and reasoning accuracy. However, indiscriminate retri…
How Reliable Are System-One Decisions in Medicine? A Comparative Study of Jev, Jev-like Models, and LLMs
Yanrui Du, Danyang Zhao, Sendong Zhao +6
Jev has attracted considerable attention for its rapid, generalizable decision-making, yet its medical reliability remains underexplored. To address this gap, our study compares va…
Didactic knowledge or Clinical Cases? How Data Types Shape Medical Large Language Models
Yuzheng Fan, Haochun Wang, Sendong Zhao +3
Medical large language models are commonly trained on mixtures of didactic data (e.g., textbooks) and clinical data (e.g., patient records), yet how these data types differentially…
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…
When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure
Boyu Xiao, Xiuqi Tian, Xuwen Song +4
Despite strong medical benchmark accuracy, LLMs can exhibit severe multi-turn sycophancy in clinical dialogue, abandoning initial correct diagnosis under escalating pressure. We pr…
GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning
Xiao Han, Yuzheng Fan, Sendong Zhao +2
Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit…
From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs
Yanrui Du, Yibo Gao, Sendong Zhao +6
R1-style LLMs have attracted growing attention for their capacity for self-reflection, yet the internal mechanisms underlying such behavior remain unclear. To bridge this gap, we a…
S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs
Yanrui Du, Sendong Zhao, Yibo Gao +9
Large language models (LLMs) equipped with chain-of-thought (CoT) achieve strong performance and offer a window into LLM behavior. However, recent evidence suggests that improvemen…
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…
ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG
Jianbo Li, Yi Jiang, Sendong Zhao +3
Retrieval-Augmented Generation (RAG) helps LLMs stay accurate, but feeding long documents into a prompt makes the model slow and expensive. This has motivated context compression,…
OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation
Yi Jiang, Sendong Zhao, Jianbo Li +4
Retrieval-Augmented Generation (RAG) improves generation quality by incorporating evidence retrieved from large external corpora. However, most existing methods rely on statically…
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…
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…
CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy
Yi Jiang, Sendong Zhao, Jianbo Li +4
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs), especially for knowledge-intensive tasks. Despite its advantages, current RAG methods often struggle to…
GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis
Yi Jiang, Sendong Zhao, Jianbo Li +2
The Retrieval-Augmented Generation (RAG) framework introduces a retrieval module to dynamically inject retrieved information into the input context of large language models (LLMs),…
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…
MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
Yanrui Du, Sendong Zhao, Danyang Zhao +6
Large Language Models (LLMs) are increasingly deployed in various applications. As their usage grows, concerns regarding their safety are rising, especially in maintaining harmless…
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…
MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts
Haoqiang Guo, Sendong Zhao, Haochun Wang +2
Deep learning is now widely used in drug discovery, providing significant acceleration and cost reduction. As the most fundamental building block, molecular representation is essen…