Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Modelsby Hengyi Wang,…
DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluationby A B M Ashikur Rahman, Saeed Anwar,…
REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropyby Haw-Shiuan Chang, Nanyun…
Estimating the Hallucination Rate of Generative AIby Andrew Jesson, Nicolas Beltran-Velez, Quentin Chu, Sweta Karlekar,…
3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucinationby Jianing Yang, Xuweiyi…
Semantically Diverse Language Generation for Uncertainty Estimation in Language Modelsby Lukas Aichberger, Kajetan Schweighofer, Mykyta…
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimizationby Yuanpu Cao,…
MetaToken: Detecting Hallucination in Image Descriptions by Meta Classificationby Laura Fieback, Jakob Spiegelberg, Hanno GottschalkFirst…
Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvementby Xiyao Wang, Jiuhai Chen,…
Scaling Laws for Discriminative Classification in Large Language Modelsby Dean Wyatte, Fatemeh Tahmasbi, Ming Li,…