Tanu Mitra
6 papers · 2024–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (2) 🌈 Renaissance Researcher (5) 🐝 Cross-Pollinator (15) 🗺️ Taxonomy Completionist (13)
🧭
Keyword Pioneer
❓
The Questioner
Conferences
EMNLP (5)
ACL (1)
Top co-authors
Keywords
large language model
(3)
value alignment
(2)
ai safety
(2)
language model
(2)
llm evaluation
(1)
behavior analysis
(1)
label efficiency
(1)
cultural bia
(1)
social bia
(1)
human annotation
(1)
social norm
(1)
misinformation detection
(1)
demographic bia
(1)
offensive language
(1)
cost reduction
(1)
ethical ai
(1)
annotator sensitivity
(1)
ethical alignment
(1)
behavioral evaluation
(1)
human-ai alignment
(1)
Papers
Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness
ACL 2025
MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform
EMNLP 2025
Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
EMNLP 2025
ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs
EMNLP 2025
“They are uncultured”: Unveiling Covert Harms and Social Threats in LLM Generated Conversations
EMNLP 2024
ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions
EMNLP 2024