SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenanceby…
Mitigating Hallucinations Using Ensemble of Knowledge Graph and Vector Store in Large Language Models to…
Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoningby Shramay Palta, Nishant Balepur, Peter Rankel,…
Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weightingby Yifan Luo, Zhennan Zhou, Meitan Wang, Bin DongFirst…
Scalable Multi-Domain Adaptation of Language Models using Modular Expertsby Peter Schafhalter, Shun Liao, Yanqi Zhou,…
QE-EBM: Using Quality Estimators as Energy Loss for Machine Translationby Gahyun Yoo, Jay Yoon LeeFirst…
Eliminating the Language Bias for Visual Question Answering with fine-grained Causal Interventionby Ying Liu, Ge…
BanglaQuAD: A Bengali Open-domain Question Answering Datasetby Md Rashad Al Hasan Rony, Sudipto Kumar Shaha,…
ForgeryGPT: Multimodal Large Language Model For Explainable Image Forgery Detection and Localizationby Jiawei Liu, Fanrui…
Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspectiveby Xiangru Zhu, Penglei Sun, Yaoxian Song,…