Knowledge representation · Graph-grounded AI · Cultural heritage
Russa Biswas
Tenure-Track Assistant Professor · Co-director, AI:PAGE-Lab
I study how explicit knowledge structures and learned language representations can strengthen one another—from knowledge-graph completion and entity typing to multilingual factuality, hallucination evaluation, and graph-grounded reasoning.
Russa’s research connects text and structured knowledge across knowledge representation, completion, and use. Building on work in graph embeddings, entity typing, and knowledge-graph completion, she develops methods and evaluations for factual and informative language models, multilingual hallucination analysis, and graph-grounded reasoning. This is a continuous programme: textual representations strengthen knowledge graphs, while explicit graph structure can make language-model outputs better supported and easier to inspect.
As co-director of AI:PAGE-Lab with historian Johan Heinsen, she brings this programme to cultural heritage by turning historical texts into searchable, connected knowledge. She also helps shape the wider research community as a co-editor of the inaugural ACL Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024).
Knowledge representation
Graph embeddings, entity typing, link prediction, and completion methods that combine graph structure with textual descriptions.
Factual and informative language models
Multilingual hallucination evaluation, factual completeness, and reasoning grounded in explicit knowledge-graph paths.
Knowledge across languages and domains
Multilingual and lower-resourced knowledge graphs, and connected historical knowledge through AI:PAGE-Lab.
Selected programmes
Projects and labs
Selected work
5 representative papers
MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations
Builds a multilingual multihop benchmark from 25,900 curated knowledge-graph paths for evaluating and reducing hallucinations.
- Knowledge, Evidence & Reasoning
- Multilingual & Lower-Resource NLP
Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective
- Knowledge, Evidence & Reasoning
- Factuality, Reliability & Evaluation
Multilingual Knowledge Graphs and Low-Resource Languages: A Review
- Knowledge, Evidence & Reasoning
- Multilingual & Lower-Resource NLP
Knowledge Graph Embeddings: Open Challenges and Opportunities
- Knowledge, Evidence & Reasoning
- Factuality, Reliability & Evaluation
MADLINK: Attentive multihop and entity descriptions for link prediction in knowledge graphs
- Knowledge, Evidence & Reasoning
Supervision and collaboration
Questions worth working on
I am interested in knowledge representation, knowledge-graph completion and reasoning, information extraction, multilingual factuality, and interdisciplinary applications of structured knowledge.