Rajeev Kumar

Rajeev Kumar, Kumar Ishan, Harishankar Kumar et al.

Disconnected data silos within enterprises obstruct the extraction of actionable insights, diminishing efficiency in areas such as product development, client engagement, meeting preparation, and analytics-driven decision-making. This paper introduces a framework that uses large language models (LLMs) to unify various data sources into a comprehensive, activity-centric knowledge graph. The framework automates tasks such as entity extraction, relationship inference, and semantic enrichment, enabling advanced querying, reasoning, and analytics across data types like emails, calendars, chats, documents, and logs. Designed for enterprise flexibility, it supports applications such as contextual search, task prioritization, expertise discovery, personalized recommendations, and advanced analytics to identify trends and actionable insights. Experimental results demonstrate its success in the discovery of expertise, task management, and data-driven decision making. By integrating LLMs with knowledge graphs, this solution bridges disconnected systems and delivers intelligent analytics-powered enterprise tools.

Rajeev Kumar, Harishankar Kumar, Kumari Shalini

Large language models have revolutionized natural language processing with their surprising capability to understand and generate human-like text. However, many of these models inherit and further amplify the biases present in their training data, raising ethical and fairness concerns. The detection and mitigation of such biases are vital to ensuring that LLMs act responsibly and equitably across diverse domains. This work investigates Knowledge Graph-Augmented Training (KGAT) as a novel method to mitigate bias in LLM. Using structured domain-specific knowledge from real-world knowledge graphs, we improve the understanding of the model and reduce biased output. Public datasets for bias assessment include Gender Shades, Bias in Bios, and FairFace, while metrics such as demographic parity and equal opportunity facilitate rigorous detection. We also performed targeted mitigation strategies to correct biased associations, leading to a significant drop in biased output and improved bias metrics. Equipped with real-world datasets and knowledge graphs, our framework is both scalable and effective, paving the way toward responsible deployment in sensitive and high-stakes applications.

Rajeev Kumar, Harishankar Kumar, Kumari Shalini

Personalized messaging plays an essential role in improving communication in areas such as healthcare, education, and professional engagement. This paper introduces a framework that uses the Knowledge Graph (KG) to dynamically rephrase written communications by integrating individual and context-specific data. The knowledge graph represents individuals, locations, and events as critical nodes, linking entities mentioned in messages to their corresponding graph nodes. The extraction of relevant information, such as preferences, professional roles, and cultural norms, is then combined with the original message and processed through a large language model (LLM) to generate personalized responses. The framework demonstrates notable message acceptance rates in various domains: 42% in healthcare, 53% in education, and 78% in professional recruitment. By integrating entity linking, event detection, and language modeling, this approach offers a structured and scalable solution for context-aware, audience-specific communication, facilitating advanced applications in diverse fields.

Ishita Doshi, Dhritiman Das, Ashish Bhutani et al.

Nearest neighbor search (NNS) has a wide range of applications in information retrieval, computer vision, machine learning, databases, and other areas. Existing state-of-the-art algorithm for nearest neighbor search, Hierarchical Navigable Small World Networks(HNSW), is unable to scale to large datasets of 100M records in high dimensions. In this paper, we propose LANNS, an end-to-end platform for Approximate Nearest Neighbor Search, which scales for web-scale datasets. Library for Large Scale Approximate Nearest Neighbor Search (LANNS) is deployed in multiple production systems for identifying topK ($100 \leq topK \leq 200$) approximate nearest neighbors with a latency of a few milliseconds per query, high throughput of 2.5k Queries Per Second (QPS) on a single node, on large ($\sim$180M data points) high dimensional (50-2048 dimensional) datasets.

Rajeev Kumar, Robert S Margolies, Rittwik Jana et al.

With the evolution of HDTV and Ultra HDTV, the bandwidth requirement for IP-based TV content is rapidly increasing. Consumers demand uninterrupted service with a high Quality of Experience (QoE). Service providers are constantly trying to differentiate themselves by innovating new ways of distributing content more efficiently with lower cost and higher penetration. In this work, we propose a cost-efficient wireless framework (WiLiTV) for delivering live TV services, consisting of a mix of wireless access technologies (e.g. Satellite, WiFi and LTE overlay links). In the proposed architecture, live TV content is injected into the network at a few residential locations using satellite dishes. The content is then further distributed to other homes using a house-to-house WiFi network or via an overlay LTE network. Our problem is to construct an optimal TV distribution network with the minimum number of satellite injection points, while preserving the highest QoE, for different neighborhood densities. We evaluate the framework using realistic time-varying demand patterns and a diverse set of home location data. Our study demonstrates that the architecture requires 75 - 90% fewer satellite injection points, compared to traditional architectures. Furthermore, we show that most cost savings can be obtained using simple and practical relay routing solutions.