3 papers
cs.LG2026
Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes
Rahul Garg, Trilok Padhi, Hemang Jain +2
Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). I…
cs.MA2025
TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems
Ishan Kavathekar, Hemang Jain, Ameya Rathod +2
Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adopt…
cs.CL2025
COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models
Priyanshul Govil, Hemang Jain, Vamshi Krishna Bonagiri +4
Large Language Models (LLMs) often inherit biases from the web data they are trained on, which contains stereotypes and prejudices. Current methods for evaluating and mitigating th…