Reihaneh Rabbany
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Reihaneh Rabbany has a total of 77 co-authors. Here are the top co-authors by number of shared publications:
- Shenyang Huang
University of Oxford, Oxford, United Kingdom
7 shared publications - Zachary Yang
La Forge, Ubisoft, Montreal, Quebec, Canada and Mila - Quebec AI Institute, Montreal, Quebec, Canada
4 shared publications - Guillaume Rabusseau
Université de Montréal
3 shared publications - Jean-François Godbout
Université de Montréal, Montreal, Quebec, Canada and Mila - Quebec AI Institute, Montreal, Quebec, Canada
3 shared publications - Nicolas Grenon-Godbout3 shared publications
- Zachary Yang
Mila -Québec AI Institute Montréal Canada
3 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9242-9253
CrediBench: Web-Scale Network Data for Credibility Prediction
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9242-9253
Open AccessCrediBench: Web-Scale Network Data for Credibility Prediction
- 12 May 2026
- Published by Taylor & Francis in Computer Science Education
- p. 1-28
A systematic review of human-LLM interactions in computational thinking empirical studies
- 12 May 2026
- Published by Taylor & Francis in Computer Science Education
- p. 1-28
A systematic review of human-LLM interactions in computational thinking empirical studies
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8717-8720
Deepfakes in the 2025 Canadian Election: Prevalence, Partisanship, and Platform Dynamics
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8717-8720
Open AccessDeepfakes in the 2025 Canadian Election: Prevalence, Partisanship, and Platform Dynamics
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 12, 11021-11024
Veracity: An Open-Source AI Fact-Checking System
The proliferation of misinformation poses a significant threat to society, exacerbated by the capabilities of generative AI. This demo paper introduces Veracity, an open-source AI system designed to empower individuals to combat misinformation through transparent and accessible fact-checking. Veracity leverages the synergy between Large Language Models (LLMs) and web retrieval agents to analyze user-submitted claims and provide grounded veracity assessments with intuitive explanations. Key features include multilingual support, numerical scoring of claim veracity, and an interactive interface inspired by familiar messaging applications. This paper will showcase Veracity's ability to not only detect misinformation but also explain its reasoning, fostering media literacy and promoting a more informed society.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 12, 11021-11024
Open AccessVeracity: An Open-Source AI Fact-Checking System
The proliferation of misinformation poses a significant threat to society, exacerbated by the capabilities of generative AI. This demo paper introduces Veracity, an open-source AI system designed to empower individuals to combat misinformation through transparent and accessible fact-checking. Veracity leverages the synergy between Large Language Models (LLMs) and web retrieval agents to analyze user-submitted claims and provide grounded veracity assessments with intuitive explanations. Key features include multilingual support, numerical scoring of claim veracity, and an interactive interface inspired by familiar messaging applications. This paper will showcase Veracity's ability to not only detect misinformation but also explain its reasoning, fostering media literacy and promoting a more informed society.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6253-6254
Responsible AI Day
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6253-6254
Open AccessResponsible AI Day
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6280-6281
Temporal Graph Learning Workshop
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6280-6281
Open AccessTemporal Graph Learning Workshop
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5161-5170
Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5161-5170
Open AccessUnified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection
- Top Cited PapersOpen Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5801-5809
A Guide to Misinformation Detection Data and Evaluation
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 5801-5809
Top Cited PapersOpen AccessA Guide to Misinformation Detection Data and Evaluation
- Open Access
Veracity: An Open-Source AI Fact-Checking System
The proliferation of misinformation poses a significant threat to society, exacerbated by the capabilities of generative AI. This demo paper introduces Veracity, an open-source AI system designed to empower individuals to combat misinformation through transparent and accessible fact-checking. Veracity leverages the synergy between Large Language Models (LLMs) and web retrieval agents to analyze user-submitted claims and provide grounded veracity assessments with intuitive explanations. Key features include multilingual support, numerical scoring of claim veracity, and an interactive interface inspired by familiar messaging applications. This paper will showcase Veracity's ability to not only detect misinformation but also explain its reasoning, fostering media literacy and promoting a more informed society.
Open AccessVeracity: An Open-Source AI Fact-Checking System
The proliferation of misinformation poses a significant threat to society, exacerbated by the capabilities of generative AI. This demo paper introduces Veracity, an open-source AI system designed to empower individuals to combat misinformation through transparent and accessible fact-checking. Veracity leverages the synergy between Large Language Models (LLMs) and web retrieval agents to analyze user-submitted claims and provide grounded veracity assessments with intuitive explanations. Key features include multilingual support, numerical scoring of claim veracity, and an interactive interface inspired by familiar messaging applications. This paper will showcase Veracity's ability to not only detect misinformation but also explain its reasoning, fostering media literacy and promoting a more informed society.
- Open Access
Weak Supervision for Real World Graphs
Node classification in real world graphs often suffers from label scarcity and noise, especially in high stakes domains like human trafficking detection and misinformation monitoring. While direct supervision is limited, such graphs frequently contain weak signals, noisy or indirect cues, that can still inform learning. We propose WSNET, a novel weakly supervised graph contrastive learning framework that leverages these weak signals to guide robust representation learning. WSNET integrates graph structure, node features, and multiple noisy supervision sources through a contrastive objective tailored for weakly labeled data. Across three real world datasets and synthetic benchmarks with controlled noise, WSNET consistently outperforms state of the art contrastive and noisy label learning methods by up to 15% in F1 score. Our results highlight the effectiveness of contrastive learning under weak supervision and the promise of exploiting imperfect labels in graph based settings.
Open AccessWeak Supervision for Real World Graphs
Node classification in real world graphs often suffers from label scarcity and noise, especially in high stakes domains like human trafficking detection and misinformation monitoring. While direct supervision is limited, such graphs frequently contain weak signals, noisy or indirect cues, that can still inform learning. We propose WSNET, a novel weakly supervised graph contrastive learning framework that leverages these weak signals to guide robust representation learning. WSNET integrates graph structure, node features, and multiple noisy supervision sources through a contrastive objective tailored for weakly labeled data. Across three real world datasets and synthetic benchmarks with controlled noise, WSNET consistently outperforms state of the art contrastive and noisy label learning methods by up to 15% in F1 score. Our results highlight the effectiveness of contrastive learning under weak supervision and the promise of exploiting imperfect labels in graph based settings.