Avijit Ghosh

5 papers · 2025–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+1 more ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) ⭐ Rising Star (5) 👥 Mega-Team · Legion

⚡ Prolific Year · Productive

Venues

AAAI (2) ICML (2) NAACL (1)

Top co-authors

Sean McGregor (2) Borhane Blili-Hamelin (2) Shayne Longpre (2) Shiri Dori-Hacohen (2) Hananel Hazan (2) Margaret Mitchell (2) Jeremy Qin (1) Mariame Tighanimine (1) Todd Snider (1) Sydney Zink (1)

Research topics

Artificial Intelligence (3) Core AI (3) Natural Language Processing (2) Resources & Methods (2) Computer Science (1) Machine Learning (1) Application Areas (1) Applications (1)

Keywords

responsible ai (1) ai safety (1) autonomous vehicle (1) ai alignment (1) human-ai interaction (1) bias evaluation (1) multilingual language model (1) stereotype detection (1) preference conflict (1) large language model (1) multi-agent system (1) misalignment quantification (1) sociotechnical system (1) alignment problem (1) bug bounty (1) safety reporting (1) jailbreak (1) safe harbor (1) coordination (1) accountability (1)

Papers

Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI ICML 2025 Position: Stop treating ‘AGI’ as the north-star goal of AI research ICML 2025 Quantifying Misalignment Between Agents: Towards a Sociotechnical Understanding of Alignment AAAI 2025 SHADES: Towards a Multilingual Assessment of Stereotypes in Large Language Models NAACL 2025 To Err Is AI: A Case Study Informing LLM Flaw Reporting Practices AAAI 2025