Selected work

Representative Papers

Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval

Jun 03, 2026

This work addresses the limitations of traditional retrieval-augmented generation (RAG) in handling complex queries—such as multi-hop reasoning and structured knowledge acquisition—where static, single-step retrieval proves inadequate. The authors propose an agent-driven adaptive RAG framework that dynamically decomposes queries, performs iterative retrieval, and incorporates a lightweight self-reflection evaluation loop to adjust retrieval strategies on demand. For the first time, the study systematically compares the efficacy of query decomposition and reflection mechanisms in structured and multi-hop settings, revealing that agent augmentation is not universally beneficial and advocating for cost-sensitive, adaptive orchestration. Experiments show a 0.04 improvement in overall score and a 0.17 gain in MRR on the DevOps dataset; however, query decomposition reduces ranking accuracy in multi-hop tasks, and while reflection enhances citation precision, it introduces notable latency.

0 citationsRead paper

XOR Bidding and Knapsack Formulations for HPC Network Resource Allocation

May 29, 2026

This work addresses the low bandwidth utilization and high transmission latency in high-performance computing centers caused by static allocation and simplistic queuing. To overcome these limitations, the authors propose a scientific-value-driven dynamic bandwidth allocation mechanism that jointly models network and computational constraints. Users participate in resource allocation through XOR bids specifying their data requirements and associated scientific value. The approach introduces two novel auction mechanisms—the greedy value-density auction and the VCG knapsack auction—balancing practical efficiency with theoretical optimality. Experimental results demonstrate that under high load, the proposed method reduces both average and tail task completion latency by over 80% compared to first-come-first-served scheduling, decreases the coefficient of variation in latency by 75–85%, and lowers the peak-to-mean network load ratio by 60–70%, substantially enhancing system stability and resource utilization efficiency.

0 citationsRead paper

Context-Aware Dialectal Arabic Machine Translation with Interactive Region and Register Selection

Apr 07, 2026

This study addresses the challenge of dialectal diversity in Arabic machine translation, where existing systems often force dialectal inputs into Modern Standard Arabic (MSA) and lack controllability over target dialectal variants. To overcome this, the authors propose a context-aware, controllable translation framework that leverages regional and sociolinguistic metadata tags to precisely govern dialectal style. They introduce a rule-based data augmentation (RBDA) method to expand a 3,000-sentence seed corpus into a balanced parallel dataset of 57,000 sentences spanning eight Arabic dialects, followed by lightweight fine-tuning of an mT5-base model. Although the model achieves a lower BLEU score (8.19) compared to NLLB (13.75), qualitative evaluation demonstrates substantially higher dialectal authenticity, with a cultural fidelity rating of 4.80/5 versus 1.0/5 for the baseline, highlighting the inadequacy of conventional automatic metrics in evaluating dialectal translation quality.

0 citationsRead paper

Chunking, Retrieval, and Re-ranking: An Empirical Evaluation of RAG Architectures for Policy Document Question Answering

Jan 21, 2026

Large language models are prone to hallucinations when answering public health policy questions, limiting their reliability in high-stakes settings. This study systematically evaluates basic and advanced Retrieval-Augmented Generation (RAG) architectures on question answering over CDC policy documents, comparing recursive character chunking with semantic chunking strategies and incorporating a cross-encoder re-ranking mechanism. Using Mistral-7B-Instruct-v0.2 as the generator and all-MiniLM-L6-v2 for embeddings, experiments demonstrate that Advanced RAG substantially improves answer faithfulness to 0.797—significantly outperforming both the vanilla LLM (0.347) and Basic RAG (0.621). These results underscore the critical role of two-stage retrieval in achieving high-fidelity responses for precise policy-related queries.

0 citationsRead paper

From Text to Returns: Using Large Language Models for Mutual Fund Portfolio Optimization and Risk-Adjusted Allocation

Dec 05, 2025

This study investigates the application of large language models (LLMs) to mutual fund portfolio optimization and risk-adjusted asset allocation. Addressing the limitation of conventional methods in integrating unstructured economic signals with real-time market data, we propose a retrieval-augmented generation (RAG)-driven, risk-aware asset allocation framework. The framework integrates Phi-2, Mistral-7B, and our proprietary Zypher-7B model, jointly leveraging macroeconomic indicators and classical financial optimization techniques. Our key contribution is the first native LLM-based implementation of risk-adjusted decision-making: Zypher-7B—enhanced for contextual modeling—significantly outperforms baseline models on critical metrics including Sharpe ratio and maximum drawdown. Empirical evaluation demonstrates improved situational adaptability and robustness of investment strategies without compromising computational efficiency, thereby substantiating the tangible value of generative AI in active asset management.

0 citationsRead paper

Recent publications

Latest Papers

Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval

Jun 03, 2026

This work addresses the limitations of traditional retrieval-augmented generation (RAG) in handling complex queries—such as multi-hop reasoning and structured knowledge acquisition—where static, single-step retrieval proves inadequate. The authors propose an agent-driven adaptive RAG framework that dynamically decomposes queries, performs iterative retrieval, and incorporates a lightweight self-reflection evaluation loop to adjust retrieval strategies on demand. For the first time, the study systematically compares the efficacy of query decomposition and reflection mechanisms in structured and multi-hop settings, revealing that agent augmentation is not universally beneficial and advocating for cost-sensitive, adaptive orchestration. Experiments show a 0.04 improvement in overall score and a 0.17 gain in MRR on the DevOps dataset; however, query decomposition reduces ranking accuracy in multi-hop tasks, and while reflection enhances citation precision, it introduces notable latency.

0 citationsRead paper

XOR Bidding and Knapsack Formulations for HPC Network Resource Allocation

May 29, 2026

This work addresses the low bandwidth utilization and high transmission latency in high-performance computing centers caused by static allocation and simplistic queuing. To overcome these limitations, the authors propose a scientific-value-driven dynamic bandwidth allocation mechanism that jointly models network and computational constraints. Users participate in resource allocation through XOR bids specifying their data requirements and associated scientific value. The approach introduces two novel auction mechanisms—the greedy value-density auction and the VCG knapsack auction—balancing practical efficiency with theoretical optimality. Experimental results demonstrate that under high load, the proposed method reduces both average and tail task completion latency by over 80% compared to first-come-first-served scheduling, decreases the coefficient of variation in latency by 75–85%, and lowers the peak-to-mean network load ratio by 60–70%, substantially enhancing system stability and resource utilization efficiency.

0 citationsRead paper

Context-Aware Dialectal Arabic Machine Translation with Interactive Region and Register Selection

Apr 07, 2026

This study addresses the challenge of dialectal diversity in Arabic machine translation, where existing systems often force dialectal inputs into Modern Standard Arabic (MSA) and lack controllability over target dialectal variants. To overcome this, the authors propose a context-aware, controllable translation framework that leverages regional and sociolinguistic metadata tags to precisely govern dialectal style. They introduce a rule-based data augmentation (RBDA) method to expand a 3,000-sentence seed corpus into a balanced parallel dataset of 57,000 sentences spanning eight Arabic dialects, followed by lightweight fine-tuning of an mT5-base model. Although the model achieves a lower BLEU score (8.19) compared to NLLB (13.75), qualitative evaluation demonstrates substantially higher dialectal authenticity, with a cultural fidelity rating of 4.80/5 versus 1.0/5 for the baseline, highlighting the inadequacy of conventional automatic metrics in evaluating dialectal translation quality.

0 citationsRead paper

Chunking, Retrieval, and Re-ranking: An Empirical Evaluation of RAG Architectures for Policy Document Question Answering

Jan 21, 2026

Large language models are prone to hallucinations when answering public health policy questions, limiting their reliability in high-stakes settings. This study systematically evaluates basic and advanced Retrieval-Augmented Generation (RAG) architectures on question answering over CDC policy documents, comparing recursive character chunking with semantic chunking strategies and incorporating a cross-encoder re-ranking mechanism. Using Mistral-7B-Instruct-v0.2 as the generator and all-MiniLM-L6-v2 for embeddings, experiments demonstrate that Advanced RAG substantially improves answer faithfulness to 0.797—significantly outperforming both the vanilla LLM (0.347) and Basic RAG (0.621). These results underscore the critical role of two-stage retrieval in achieving high-fidelity responses for precise policy-related queries.

0 citationsRead paper

From Text to Returns: Using Large Language Models for Mutual Fund Portfolio Optimization and Risk-Adjusted Allocation

Dec 05, 2025

This study investigates the application of large language models (LLMs) to mutual fund portfolio optimization and risk-adjusted asset allocation. Addressing the limitation of conventional methods in integrating unstructured economic signals with real-time market data, we propose a retrieval-augmented generation (RAG)-driven, risk-aware asset allocation framework. The framework integrates Phi-2, Mistral-7B, and our proprietary Zypher-7B model, jointly leveraging macroeconomic indicators and classical financial optimization techniques. Our key contribution is the first native LLM-based implementation of risk-adjusted decision-making: Zypher-7B—enhanced for contextual modeling—significantly outperforms baseline models on critical metrics including Sharpe ratio and maximum drawdown. Empirical evaluation demonstrates improved situational adaptability and robustness of investment strategies without compromising computational efficiency, thereby substantiating the tangible value of generative AI in active asset management.

0 citationsRead paper