Debanjana Kar

6 papers · 2021–2026 · 5 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 ↓

🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 👥 Mega-Team · Squad

Venues

AAAI (2) AACL (1) ACL (1) EMNLP (1) ICML (1)

Top co-authors

Prateeti Mohapatra (3) Pooja Aggarwal (2) Pawan Goyal (2) Sudeshna Sarkar (2) Suranjana Samanta (2) Oishik Chatterjee (2) Pranjal Gupta (2) Ruchi Mahindru (2) Ting Dai (2) Harshit Kumar (2)

Research topics

Artificial Intelligence (3) Core AI (3) Machine Learning (2) Natural Language Processing (2) Applications (2) Deep Learning (1) Interdisciplinary (1) Application Areas (1) Generation (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Resources & Methods (1) Social (1)

Keywords

large language model (3) document-level extraction (2) event argument extraction (2) site reliability engineering (2) argument extraction (1) multimodal learning (1) emotion recognition (1) code generation (1) multilingual text generation (1) educational technology (1) emotion detection (1) affective computing (1) prompt-based method (1) ai agent (1) log analysis (1) facial expression (1) cpu inference (1) pedagogical strategy (1) document-level processing (1) multimodal emotion recognition (1)

Papers

Scalable and Efficient Large-Scale Log Analysis with LLMs: An IT Software Support Case Study AAAI 2026 ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks ICML 2025 MathBuddy: A Multimodal System for Affective Math Tutoring EMNLP 2025 ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement AAAI 2025 ArgGen: Prompting Text Generation Models for Document-Level Event-Argument Aggregation AACL 2022 ArgFuse: A Weakly-Supervised Framework for Document-Level Event Argument Aggregation ACL 2021