Yiwei Wang

Latest

Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
A Survey of Vibe Coding with Large Language Models
Not in Sync: Unveiling Temporal Bias in Audio Chat Models
Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
Context-DPO: Aligning Language Models for Context-Faithfulness
A Survey of Context Engineering for Large Language Models
Context Engineering for Large Language Models: A Comprehensive Survey
RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?
Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation
Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts
Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness Benchmark
"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak
a1: Steep Test-time Scaling Law via Environment Augmented Generation
Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models
"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak
Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities
HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router
LPNL: Scalable Link Prediction with Large Language Models
SLANG: New Concept Comprehension of Large Language Models
SLANG: New Concept Comprehension of Large Language Models
StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models
Provably Robust Node Classification via Low-Pass Message Passing