Russa Biswas

5 papers · 2024–2025 · 4 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 · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird

Venues

EMNLP (2) AAAI (1) ACL (1) NAACL (1)

Top co-authors

Gerard de Melo (3) Yiyi Chen (2) Johannes Bjerva (2) Heather Lent (1) Roi Cohen (1) Qiongxiu Li (1) Adrian Ziupka (1) Tolga Buz (1) Necdet Güven (1) Jasmin Geppert (1)

Research topics

Natural Language Processing (5) Resources & Methods (4) Artificial Intelligence (3) Core AI (3) Applications (2) Machine Learning (1) Security & Privacy (1) Application Areas (1) Privacy (1)

Keywords

large language model (2) language confusion (2) security vulnerability (2) adversarial attack (1) structured data (1) domain-specific knowledge (1) multilingual embedding (1) multilingual language model (1) embedding inversion (1) cross-lingual attack (1) preference dataset (1) long-form question answering (1) linguistic typology (1) financial text (1) knowledge base population (1) llm security (1) language entropy (1) language model security (1) embedding inversion attack (1) cross-script inversion (1)

Papers

Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks AAAI 2025 InFact: Informativeness Alignment for Improved LLM Factuality EMNLP 2025 Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis NAACL 2025 LLMs Cannot (Yet) Match the Specificity and Simplicity of Online Communities in Long Form Question Answering EMNLP 2024 Wiki-VEL: Visual Entity Linking for Structured Data on Wikimedia Commons ACL 2024