17 citations · 52 across the 18 of their papers we have counts for
19 papers
When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs
Apoorva Upadhyaya, Sandipan Sikdar
Safety alignment of large language models (LLMs) degrades across languages, yet the internal mechanism driving this asymmetry remains poorly understood. Our work, therefore, presen…
REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease Inference
Anurag Sharma, Sai Teja Chunchu, Prasenjit Mitra +2
Language models trained for clinical disease inference are trained on patient data, which may include sensitive and private information, and data owners may request the removal of…
Towards Sensitivity-Aware Language Models
Dren Fazlija, Iyiola E. Olatunji, Daniel Kudenko +1
With LLMs increasingly deployed in corporate data management, it is crucial to ensure that these models do not leak sensitive information. In the context of corporate data manageme…
ACCESS DENIED INC: The First Benchmark Environment for Sensitivity Awareness
Dren Fazlija, Arkadij Orlov, Sandipan Sikdar
Large language models (LLMs) are increasingly becoming valuable to corporate data management due to their ability to process text from various document formats and facilitate user…
Exploring Disparity-Accuracy Trade-offs in Face Recognition Systems: The Role of Datasets, Architectures, and Loss Functions
Siddharth D Jaiswal, Sagnik Basu, Sandipan Sikdar +1
Automated Face Recognition Systems (FRSs), developed using deep learning models, are deployed worldwide for identity verification and facial attribute analysis. The performance of…
Recommendation Fairness in Social Networks Over Time
Meng Cao, Hussain Hussain, Sandipan Sikdar +3
In social recommender systems, it is crucial that the recommendation models provide equitable visibility for different demographic groups, such as gender or race. Most existing res…
IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers
Jingge Xiao, Leonie Basso, Wolfgang Nejdl +2
Continuous-time models such as Neural ODEs and Neural Flows have shown promising results in analyzing irregularly sampled time series frequently encountered in electronic health re…
A Review of the Role of Causality in Developing Trustworthy AI Systems
Niloy Ganguly, Dren Fazlija, Maryam Badar +9
State-of-the-art AI models largely lack an understanding of the cause-effect relationship that governs human understanding of the real world. Consequently, these models do not gene…
SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings
Jan Engler, Sandipan Sikdar, Marlene Lutz +1
Adding interpretability to word embeddings represents an area of active research in text representation. Recent work has explored thepotential of embedding words via so-called pola…
Properties of Group Fairness Metrics for Rankings
Tobias Schumacher, Marlene Lutz, Sandipan Sikdar +1
In recent years, several metrics have been developed for evaluating group fairness of rankings. Given that these metrics were developed with different application contexts and rank…
Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks
Hussain Hussain, Meng Cao, Sandipan Sikdar +4
We present evidence for the existence and effectiveness of adversarial attacks on graph neural networks (GNNs) that aim to degrade fairness. These attacks can disadvantage a partic…
The Effects of Gender Signals and Performance in Online Product Reviews
Sandipan Sikdar, Rachneet Singh Sachdeva, Johannes Wachs +2
This work quantifies the effects of signaling and performing gender on the success of reviews written on the popular amazon shopping platform. Highly rated reviews play an importan…
The POLAR Framework: Polar Opposites Enable Interpretability of Pre-Trained Word Embeddings
Binny Mathew, Sandipan Sikdar, Florian Lemmerich +1
We introduce POLAR - a framework that adds interpretability to pre-trained word embeddings via the adoption of semantic differentials. Semantic differentials are a psychometric con…
StRE: Self Attentive Edit Quality Prediction in Wikipedia
Soumya Sarkar, Bhanu Prakash Reddy, Sandipan Sikdar +1
Wikipedia can easily be justified as a behemoth, considering the sheer volume of content that is added or removed every minute to its several projects. This creates an immense scop…
Using Core-Periphery Structure to Predict High Centrality Nodes in Time-Varying Networks
Soumya Sarkar, Sandipan Sikdar, Animesh Mukherjee +1
Vertices with high betweenness and closeness centrality represent influential entities in a network. An important problem for time varying networks is to know a-priori, using minim…
ComPAS: Community Preserving Sampling for Streaming Graphs
Sandipan Sikdar, Tanmoy Chakraborty, Soumya Sarkar +2
In the era of big data, graph sampling is indispensable in many settings. Existing sampling methods are mostly designed for static graphs, and aim to preserve basic structural prop…
Influence of Reviewer Interaction Network on Long-term Citations: A Case Study of the Scientific Peer-Review System of the Journal of High Energy Physics
Sandipan Sikdar, Matteo Marsili, Niloy Ganguly +1
A `peer-review system' in the context of judging research contributions, is one of the prime steps undertaken to ensure the quality of the submissions received, a significant porti…
Anomalies in the peer-review system: A case study of the journal of High Energy Physics
Sandipan Sikdar, Matteo Marsili, Niloy Ganguly +1
Peer-review system has long been relied upon for bringing quality research to the notice of the scientific community and also preventing flawed research from entering into the lite…
Time series analysis of temporal networks
Sandipan Sikdar, Niloy Ganguly, Animesh Mukherjee
An important feature of all real-world networks is that the network structure changes over time. Due to this dynamic nature, it becomes difficult to propose suitable growth models…