FLaMe Research Lab

If you're interested, here’s the paper (preprint) for a deeper dive into our work: lnkd.in/gn-WJiF2

Our research, titled "𝗙𝗶𝗻𝗲-𝗴𝗿𝗮𝗶𝗻𝗲𝗱 𝗡𝗮𝗿𝗿𝗮𝘁𝗶𝘃𝗲 𝗖𝗹𝗮𝘀𝘀𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻 𝗶𝗻 𝗕𝗶𝗮𝘀𝗲𝗱 𝗡𝗲𝘄𝘀 𝗔𝗿𝘁𝗶𝗰𝗹𝗲𝘀," presents an innovative way to examine how narratives influence biased news reporting and propaganda.

We are absolutely delighted to announce that our paper has been accepted for presentation at the 𝘓𝘢𝘯𝘨𝘶𝘢𝘨𝘦 𝘙𝘦𝘴𝘰𝘶𝘳𝘤𝘦𝘴 𝘢𝘯𝘥 𝘌𝘷𝘢𝘭𝘶𝘢𝘵𝘪𝘰𝘯 𝘊𝘰𝘯𝘧𝘦𝘳𝘦𝘯𝘤𝘦 (𝘓𝘙𝘌𝘊) 2026! #NLP #ComputationalLinguistics #PropagandaAnalysis #LREC2026 #LanguageResource

We are thrilled to announce the public release of our AxiOM and Restore dataset, accepted at The Web Conference (The Web Conference'25)! 📄 Read the full paper here: arxiv.org/pdf/2501.15321 DatasetGitHubRepository: github.com/flamenlp/M3H

Our findings show a significant improvement in classifying mental health symptoms expressed in memes, highlighting importance of integrating commonsense understanding in AI models. Check out the full paper here: arxiv.org/abs/2501.15321 #TheWebConference #MentalHealth 3/3

AxiOM: A dataset mapping memes to six fine-grained anxiety symptoms using the GAD questionnaire. M3H: A commonsense & domain-enriched framework enhancing Multimodal LMs’ figurative language understanding. #NLProc #Research 2/3

#WWW | Excited to share our latest research on enhancing the understanding of mental health expressions in memes! In our paper, "Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification," we introduce... #AI #MentalHealth #NLProc 1/3

🎉 Excited to share that our work has been accepted to #Findings of NAACL 2025! 📜 Title: Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation 👥 Authors: Palaash Goel, Dushyant Singh Chauhan, Md Shad Akhtar #NAACL2025 #NLP #Multimodal #AIResearch

This work is in collabration with @thisisUIC !! Authors: Abdullah Mazhar, Zuhair hasan Shaik, Aseem Srivastava, Polly Ruhnke, Lavanya Vaddavalli, Sri Keshav Katragadda, Shweta Yadav, Md Shad Akhtar 2/n

#WWW2025 | Our work has been accepted for oral presentation at TheWebConf 2025 Title: Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification Stay tuned for preprint, data, and code on our lab's webpage: @flamenlp 1/n

𝐂𝐎𝐋𝐈𝐍𝐆 '25 𝐀𝐜𝐜𝐞𝐩𝐭𝐚𝐧𝐜𝐞‼️ We are pleased to share that our paper accepted at COLING 2025. Title: 𝐐𝐔𝐄𝐍𝐂𝐇: 𝐌𝐞𝐚𝐬𝐮𝐫𝐢𝐧𝐠 𝐭𝐡𝐞 𝐠𝐚𝐩 𝐛𝐞𝐭𝐰𝐞𝐞𝐧 𝐈𝐧𝐝𝐢𝐜 𝐚𝐧𝐝 𝐍𝐨𝐧-𝐈𝐧𝐝𝐢𝐜 𝐂𝐨𝐧𝐭𝐞𝐱𝐭𝐮𝐚𝐥 𝐆𝐞𝐧𝐞𝐫𝐚𝐥 𝐑𝐞𝐚𝐬𝐨𝐧𝐢𝐧𝐠 𝐢𝐧 𝐋𝐋𝐌𝐬