Krishnasuri Narayanam

Ashlesha Akella, Akshar Kaul, Krishnasuri Narayanam et al.

Reliable data quality is crucial for downstream analysis of tabular datasets, yet rule-based validation often struggles with inefficiency, human intervention, and high computational costs. We present a three-stage framework that combines statistical inliner detection with LLM-driven rule and code generation. After filtering data samples through traditional clustering, we iteratively prompt LLMs to produce semantically valid quality rules and synthesize their executable validators through code-generating LLMs. To generate reliable quality rules, we aid LLMs with retrieval-augmented generation (RAG) by leveraging external knowledge sources and domain-specific few-shot examples. Robust guardrails ensure the accuracy and consistency of both rules and code snippets. Extensive evaluations on benchmark datasets confirm the effectiveness of our approach.

Ashlesha Akella, Krishnasuri Narayanam

Ensuring data quality in large tabular datasets is a critical challenge, typically addressed through data wrangling tasks. Traditional statistical methods, though efficient, cannot often understand the semantic context and deep learning approaches are resource-intensive, requiring task and dataset-specific training. To overcome these shortcomings, we present an automated system that utilizes large language models to generate executable code for tasks like missing value imputation, error detection, and error correction. Our system aims to identify inherent patterns in the data while leveraging external knowledge, effectively addressing both memory-dependent and memory-independent tasks.

Abhijit Manatkar, Ashlesha Akella, Parthivi Gupta et al.

Discovering meaningful insights from a large dataset, known as Exploratory Data Analysis (EDA), is a challenging task that requires thorough exploration and analysis of the data. Automated Data Exploration (ADE) systems use goal-oriented methods with Large Language Models and Reinforcement Learning towards full automation. However, these methods require human involvement to anticipate goals that may limit insight extraction, while fully automated systems demand significant computational resources and retraining for new datasets. We introduce QUIS, a fully automated EDA system that operates in two stages: insight generation (ISGen) driven by question generation (QUGen). The QUGen module generates questions in iterations, refining them from previous iterations to enhance coverage without human intervention or manually curated examples. The ISGen module analyzes data to produce multiple relevant insights in response to each question, requiring no prior training and enabling QUIS to adapt to new datasets.

Krishnasuri Narayanam, Venkatraman Ramakrishna, Dhinakaran Vinayagamurthy et al.

A core enabler for blockchain or DLT interoperability is the ability to atomically exchange assets held by mutually untrusting owners on different ledgers. This atomic swap problem has been well-studied, with the Hash Time Locked Contract (HTLC) emerging as a canonical solution. HTLC ensures atomicity of exchange, albeit with caveats for node failure and timeliness of claims. But a bigger limitation of HTLC is that it only applies to a model consisting of two adversarial parties having sole ownership of a single asset in each ledger. Realistic extensions of the model in which assets may be jointly owned by multiple parties, all of whose consents are required for exchanges, or where multiple assets must be exchanged for one, are susceptible to collusion attacks and hence cannot be handled by HTLC. In this paper, we generalize the model of asset exchanges across DLT networks and present a taxonomy of use cases, describe the threat model, and propose MPHTLC, an augmented HTLC protocol for atomic multi-owner-and-asset exchanges. We analyze the correctness, safety, and application scope of MPHTLC. As proof-of-concept, we show how MPHTLC primitives can be implemented in networks built on Hyperledger Fabric and Corda, and how MPHTLC can be implemented in the Hyperledger Labs Weaver framework by augmenting its existing HTLC protocol.

Diddigi Raghuram Bharadwaj, Sai Koti Reddy Danda, Krishnasuri Narayanam et al.

This paper considers two important problems -- on the supply-side and demand-side respectively and studies both in a unified framework. On the supply side, we study the problem of energy sharing among microgrids with the goal of maximizing profit obtained from selling power while at the same time not deviating much from the customer demand. On the other hand, under shortage of power, this problem becomes one of deciding the amount of power to be bought with dynamically varying prices. On the demand side, we consider the problem of optimally scheduling the time-adjustable demand - i.e., of loads with flexible time windows in which they can be scheduled. While previous works have treated these two problems in isolation, we combine these problems together and provide a unified Markov decision process (MDP) framework for these problems. We then apply the Q-learning algorithm, a popular model-free reinforcement learning technique, to obtain the optimal policy. Through simulations, we show that the policy obtained by solving our MDP model provides more profit to the microgrids.