Excited to share that our paper on KID-VLM has been accepted to #ACL2025 Findings! 🎉 This work is a nice addition to a growing but still underexplored area of #NeurosymbolicAI approaches for complex social issues 🧩. We believe these methods will provide significant advances in both prediction and generation tasks, especially where nuance and context matter. Our work develops a #NeurosymbolicAI approach, KID-VLM, that combines the #LVLMs and commonsense #KnowledgeGraphs to detect subtle and context-rich cues of #OnlineToxicity. #OnlineToxicity often disguises itself behind sarcasm, dark humor, and cultural nuance. Our approach bridges the gap between implicit signals in neural models and explicit reasoning through symbolic knowledge, improving recall, accuracy, and interpretability. Read the preprint 📜: arxiv.org/abs/2411.12174 Thanks to our amazing team for pushing this forward, and to the ACL community for recognizing this effort! with @trilokpadhi_ Rahul Garg, Hemang Jain, @ponguru #ACL2025 #NeuroSymbolicAI #OnlineToxicity #CommonsenseAI #LVLMs #LLMs