Fali Wang
YOU?
Author Swipe
View article: Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking
Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking Open
Knowledge Graph Question Answering (KGQA) systems rely on high-quality benchmarks to evaluate complex multi-hop reasoning. However, despite their widespread use, popular datasets such as WebQSP and CWQ suffer from critical quality issues, …
View article: SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models Open
This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing …
View article: HC-GST: Heterophily-aware Distribution Consistency based Graph Self-training
HC-GST: Heterophily-aware Distribution Consistency based Graph Self-training Open
Graph self-training (GST), which selects and assigns pseudo-labels to unlabeled nodes, is popular for tackling label sparsity in graphs. However, recent study on homophily graphs show that GST methods could introduce and amplify distributi…
View article: Enhance Graph Alignment for Large Language Models
Enhance Graph Alignment for Large Language Models Open
Graph-structured data is prevalent in the real world. Recently, due to the powerful emergent capabilities, Large Language Models (LLMs) have shown promising performance in modeling graphs. The key to effectively applying LLMs on graphs is …
View article: Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels
Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels Open
Few-shot node classification poses a significant challenge for Graph Neural\nNetworks (GNNs) due to insufficient supervision and potential distribution\nshifts between labeled and unlabeled nodes. Self-training has emerged as a\nwidely pop…
View article: InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration
InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration Open
Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integratin…
View article: Maximum Entropy Loss, the Silver Bullet Targeting Backdoor Attacks in Pre-trained Language Models
Maximum Entropy Loss, the Silver Bullet Targeting Backdoor Attacks in Pre-trained Language Models Open
Pre-trained language model (PLM) can be stealthily misled to target outputs by backdoor attacks when encountering poisoned samples, without performance degradation on clean samples. The stealthiness of backdoor attacks is commonly attained…