Shuzhou Yuan
YOU?
Author Swipe
View article: Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs
Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs Open
Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark…
View article: LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification
LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification Open
Detoxification, the task of rewriting harmful language into non-toxic text, has become increasingly important amid the growing prevalence of toxic content online. However, high-quality parallel datasets for detoxification, especially for h…
View article: Explainable LiDAR 3D Point Cloud Segmentation and Clustering for Detecting Airplane-Generated Wind Turbulence
Explainable LiDAR 3D Point Cloud Segmentation and Clustering for Detecting Airplane-Generated Wind Turbulence Open
View article: Explainable LiDAR 3D Point Cloud Segmentation and Clustering for Detecting Airplane-Generated Wind Turbulence
Explainable LiDAR 3D Point Cloud Segmentation and Clustering for Detecting Airplane-Generated Wind Turbulence Open
Wake vortices - strong, coherent air turbulences created by aircraft - pose a significant risk to aviation safety and therefore require accurate and reliable detection methods. In this paper, we present an advanced, explainable machine lea…
View article: Can Hallucinations Help? Boosting LLMs for Drug Discovery
Can Hallucinations Help? Boosting LLMs for Drug Discovery Open
Hallucinations in large language models (LLMs), plausible but factually inaccurate text, are often viewed as undesirable. However, recent work suggests that such outputs may hold creative potential. In this paper, we investigate whether ha…
View article: Graph-Guided Textual Explanation Generation Framework
Graph-Guided Textual Explanation Generation Framework Open
View article: Graph-Guided Textual Explanation Generation Framework
Graph-Guided Textual Explanation Generation Framework Open
Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the…
View article: GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism
GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism Open
Pretrained Language Models (PLMs) benefit from external knowledge stored in graph structures for various downstream tasks. However, bridging the modality gap between graph structures and text remains a significant challenge. Traditional me…
View article: Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models
Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models Open
Probing the multilingual knowledge of linguistic structure in LLMs, often characterized as sequence labeling, faces challenges with maintaining output templates in current text-to-text prompting strategies. To solve this, we introduce a de…
View article: Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers
Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers Open
Large Language Models (LLMs) possess outstanding capabilities in addressing various natural language processing (NLP) tasks. However, the sheer size of these models poses challenges in terms of storage, training and inference due to the in…
View article: GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network
GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network Open
Large Language Models (LLMs) exhibit strong In-Context Learning (ICL) capabilities when prompts with demonstrations are used. However, fine-tuning still remains crucial to further enhance their adaptability. Prompt-based fine-tuning proves…
View article: ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks
ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks Open
Prompt-based methods have been successfully applied to multilingual pretrained language models for zero-shot cross-lingual understanding. However, most previous studies primarily focused on sentence-level classification tasks, and only a f…
View article: ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks
ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks Open
View article: Evaluating Generative Models for Graph-to-Text Generation
Evaluating Generative Models for Graph-to-Text Generation Open
Large language models (LLMs) have been widely employed for graph-to-text generation tasks. However, the process of finetuning LLMs requires significant training resources and annotation work. In this paper, we explore the capability of gen…
View article: Biases in scholarly recommender systems: impact, prevalence, and mitigation
Biases in scholarly recommender systems: impact, prevalence, and mitigation Open
With the remarkable increase in the number of scientific entities such as publications, researchers, and scientific topics, and the associated information overload in science, academic recommender systems have become increasingly important…
View article: Biases in Scholarly Recommender Systems: Impact, Prevalence, and Mitigation
Biases in Scholarly Recommender Systems: Impact, Prevalence, and Mitigation Open
With the remarkable increase in the number of scientific entities such as publications, researchers, and scientific topics, and the associated information overload in science, academic recommender systems have become increasingly important…
View article: Evaluating Generative Models for Graph-to-Text Generation
Evaluating Generative Models for Graph-to-Text Generation Open
Large language models (LLMs) have been widely employed for graph-to-text generation tasks.However, the process of finetuning LLMs requires significant training resources and annotation work.In this paper, we explore the capability of gener…
View article: Separating Hate Speech and Offensive Language Classes via Adversarial Debiasing
Separating Hate Speech and Offensive Language Classes via Adversarial Debiasing Open
Research to tackle hate speech plaguing online media has made strides in providing solutions, analyzing bias and curating data. A challenging problem is ambiguity between hate speech and offensive language, causing low performance both ove…