Ruifeng Xu
YOU?
Author Swipe
View article: LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings Open
Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A recent black-box method has attempted to incorporate textual and structural information to en…
View article: Assessing the Impact of Methodological Assumptions on Estimated Age of Disease-Causal Human Papillomavirus Infection in US Females
Assessing the Impact of Methodological Assumptions on Estimated Age of Disease-Causal Human Papillomavirus Infection in US Females Open
We adapted a previous discrete event simulation model to assess the impact of varying time distributions from disease-causal human papillomavirus (HPV) infection to CIN2+ onset on the estimated age distribution of disease-casual infection …
View article: A Survey on Large Language Model Benchmarks
A Survey on Large Language Model Benchmarks Open
In recent years, with the rapid development of the depth and breadth of large language models' capabilities, various corresponding evaluation benchmarks have been emerging in increasing numbers. As a quantitative assessment tool for model …
View article: Cost-effectiveness analysis of pembrolizumab as an adjuvant treatment of early-stage non-small cell lung cancer following complete resection and platinum-based chemotherapy in Canada
Cost-effectiveness analysis of pembrolizumab as an adjuvant treatment of early-stage non-small cell lung cancer following complete resection and platinum-based chemotherapy in Canada Open
Adjuvant pembrolizumab was found to be cost-effective compared to routine observation from the public healthcare payer perspective in Canada.
View article: Meta-Learning for Incomplete Multimodal Sentiment Analysis
Meta-Learning for Incomplete Multimodal Sentiment Analysis Open
View article: Predicting Lung Cancer EGFR Mutation Status via Integration of Deep Learning and Radiomics in Pulmonary CT Imaging
Predicting Lung Cancer EGFR Mutation Status via Integration of Deep Learning and Radiomics in Pulmonary CT Imaging Open
In the spectrum of mortality cases attributed to malignancies, lung cancer holds a prominent position. Mutations in the epidermal growth factor receptor (EGFR) are crucial in both the development and therapy of non-small cell lung cancer (…
View article: KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning Open
Recent advances in large language model (LLM) post-training have leveraged two distinct paradigms to enhance reasoning capabilities: reinforcement learning (RL) and knowledge distillation (KD). While RL enables the emergence of complex rea…
View article: Ablation combined with video-assisted thoracic surgery hybrid technique for multiple primary lung cancer
Ablation combined with video-assisted thoracic surgery hybrid technique for multiple primary lung cancer Open
Increased public health awareness and expanded low-dose computed tomography (CT) utilization, accelerated by the COVID-19 pandemic, have elevated detection rates of pulmonary ground-glass nodules (GGNs). Patients with multiple primary lung…
View article: BeyondGender: A Multifaceted Bilingual Dataset for Practical Sexism Detection
BeyondGender: A Multifaceted Bilingual Dataset for Practical Sexism Detection Open
Sexism affects both women and men, yet research often overlooks misandry and suffers from overly broad annotations that limit AI applications. To address this, we introduce BeyondGender, a dataset meticulously annotated according to the la…
View article: Training on the Benchmark Is Not All You Need
Training on the Benchmark Is Not All You Need Open
The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests …
View article: A New Formula for Sticker Retrieval: Reply with Stickers in Multi-Modal and Multi-Session Conversation
A New Formula for Sticker Retrieval: Reply with Stickers in Multi-Modal and Multi-Session Conversation Open
Stickers are widely used in online chatting, which can vividly express someone's intention, emotion, or attitude. Existing conversation research typically retrieves stickers based on a single session or the previous textual information, wh…
View article: Integrated analysis of tyrosine-induced MiRNA and mRNA expression profiles in melanocytes reveals the regulatory role of miR-1560-3p in melanin deposition in Xichuan black-bone chickens
Integrated analysis of tyrosine-induced MiRNA and mRNA expression profiles in melanocytes reveals the regulatory role of miR-1560-3p in melanin deposition in Xichuan black-bone chickens Open
We found that tyrosine promoted the proliferation and migration of melanocytes, and expression profile analysis identified 57 differentially expressed mRNAs (DEGs) and 19 differentially expressed miRNAs (DEMs). Fifty miRNA‒mRNA target gene…
View article: Character Can Speak Directly: An End-to-End Character Region Excavation Network for Scene Text Spotting
Character Can Speak Directly: An End-to-End Character Region Excavation Network for Scene Text Spotting Open
End-to-end scene text spotting methods have garnered significant research attention due to their promising results. However, most existing approaches are not well suited for real-world applications because of their inherently complex pipel…
View article: Corrigendum: Adverse drug events (ADEs) risk signal mining related to eculizumab based on the FARES database
Corrigendum: Adverse drug events (ADEs) risk signal mining related to eculizumab based on the FARES database Open
[This corrects the article DOI: 10.3389/fphar.2024.1440907.].
View article: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking Open
Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…
View article: AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling
AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling Open
Traditional in-person psychological counseling remains primarily niche, often chosen by individuals with psychological issues, while online automated counseling offers a potential solution for those hesitant to seek help due to feelings of…
View article: Adverse drug events (ADEs) risk signal mining related to eculizumab based on the FARES database
Adverse drug events (ADEs) risk signal mining related to eculizumab based on the FARES database Open
Introduction Eculizumab is a C5 complement inhibitor approved by the FDA for the targeted treatment of four rare diseases, paroxysmal nocturnal hemoglobinuria (PNH), atypical hemolytic uremic syndrome (aHUS), generalized myasthenia gravis …
View article: Sparse Activation Editing for Reliable Instruction Following in Narratives
Sparse Activation Editing for Reliable Instruction Following in Narratives Open
View article: DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis
DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis Open
View article: Targeted Distillation for Sentiment Analysis
Targeted Distillation for Sentiment Analysis Open
View article: A Multi-persona Framework for Argument Quality Assessment
A Multi-persona Framework for Argument Quality Assessment Open
View article: Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework
Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework Open
View article: Exploring Quality and Diversity in Synthetic Data Generation for Argument Mining
Exploring Quality and Diversity in Synthetic Data Generation for Argument Mining Open
View article: Error Comparison Optimization for Large Language Models on Aspect-Based Sentiment Analysis
Error Comparison Optimization for Large Language Models on Aspect-Based Sentiment Analysis Open
View article: Distilling Fine-grained Sentiment Understanding from Large Language Models
Distilling Fine-grained Sentiment Understanding from Large Language Models Open
Fine-grained sentiment analysis (FSA) aims to extract and summarize user opinions from vast opinionated text. Recent studies demonstrate that large language models (LLMs) possess exceptional sentiment understanding capabilities. However, d…
View article: DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis
DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis Open
Recently developed large language models (LLMs) have presented promising new avenues to address data scarcity in low-resource scenarios. In few-shot aspect-based sentiment analysis (ABSA), previous efforts have explored data augmentation t…
View article: Multi-Task Model Merging via Adaptive Weight Disentanglement
Multi-Task Model Merging via Adaptive Weight Disentanglement Open
Model merging has recently gained attention as an economical and scalable approach to incorporate task-specific weights from various tasks into a unified multi-task model. For example, in Task Arithmetic (TA), adding the fine-tuned weights…
View article: Comprehensive analysis of surgical strategies and prognosis for non-small cell lung cancer with pleural metastasis detected intraoperatively
Comprehensive analysis of surgical strategies and prognosis for non-small cell lung cancer with pleural metastasis detected intraoperatively Open
Our study supports the implementation of major tumor resection in patients with pleural metastasis detected intraoperatively but not lymph node dissection or the resection of pleural metastatic lesions. Postoperative chemotherapy is also n…
View article: A Comparison-Based Framework for Argument Quality Assessment
A Comparison-Based Framework for Argument Quality Assessment Open
Assessing the quality of arguments is both valuable and challenging. Humans often find that making pairwise comparisons between a target argument and several reference arguments facilitates a more precise judgment of the target argument’s …
View article: A Hybrid Approach to Dimensional Aspect-Based Sentiment Analysis Using BERT and Large Language Models
A Hybrid Approach to Dimensional Aspect-Based Sentiment Analysis Using BERT and Large Language Models Open
Dimensional aspect-based sentiment analysis (dimABSA) aims to recognize aspect-level quadruples from reviews, offering a fine-grained sentiment description for user opinions. A quadruple consists of aspect, category, opinion, and sentiment…