Bharathi Raja Chakravarthi

Multi-agent framework for span-level detection of homophobic and transphobic comments in Hindi

Social media platforms serve as spaces for both open expression and the spread of harmful narratives, often targeting marginalized communities. In the context of Hindi, automated detection of homophobic and transphobic comments at span level is still not studied widely. This work introduces a span-annotated dataset...

Overview of the CC-MMD 2026 Grand Challenge: Cross-Cultural Misogynistic Meme Detection in Multimodal Memes

The Cross-Cultural Misogynistic Meme Detection Grand Challenge, CC-MMD 2026, addresses the problem of identifying misogynistic content in multimodal memes across culturally diverse annotation perspectives. Existing misogyny detection benchmarks have advanced multimodal content moderation, but most assume a single groun...

Vivatham: a multi-agent debate framework for generating counter-narratives against homophobia and transphobia in Tamil

A newly curated dataset comprising 5,428 Tamil HS-CN pairs is introduced and VIVATHAM, a novel multi-agent persona debate framework for generating high quality Tamil counter-narratives is proposed, demonstrating that the multi-agent debate framework significantly outperforms standard CN generation approaches.

From transformer to large language models for automated generation of hospital discharge summaries: a systematic review

Knowledge-augmented multimodal framework for detecting and countering misogynistic memes

Results indicate that the proposed ToxiLEN framework improves Chinese misogynistic meme detection and generates CNs that are contextually aligned and less repetitive than the evaluated baselines.