Logic-Enhanced Language Model Agents for Trustworthy Social Simulationsby Agnieszka Mensfelt, Kostas Stathis, Vince TrencsenyiFirst submitted…
FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench…
Toward Automated Simulation Research Workflow through LLM Prompt Engineering Designby Zhihan Liu, Yubo Chai, Jianfeng…
A Survey on Evaluation of Multimodal Large Language Modelsby Jiaxing Huang, Jingyi ZhangFirst submitted to…
Atoxia: Red-teaming Large Language Models with Target Toxic Answersby Yuhao Du, Zhuo Li, Pengyu Cheng,…
Probing Causality Manipulation of Large Language Modelsby Chenyang Zhang, Haibo Tong, Bin Zhang, Dongyu ZhangFirst…
Tangram: Benchmark for Evaluating Geometric Element Recognition in Large Multimodal Modelsby Chao Zhang, Jiamin Tang,…
CodeGraph: Enhancing Graph Reasoning of LLMs with Codeby Qiaolong Cai, Zhaowei Wang, Shizhe Diao, James…
LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Modelsby Qihang Ge, Wei Sun, Yu Zhang,…
GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person Perspectiveby Ala N. Tak, Jonathan GratchFirst submitted…