Sai Munikoti

Rounak Meyur, Hung Phan, Koby Hayashi et al.

The National Environment Policy Act (NEPA) stands as a foundational piece of environmental legislation in the United States, requiring federal agencies to consider the environmental impacts of their proposed actions. The primary mechanism for achieving this is through the preparation of Environmental Assessments (EAs) and, for significant impacts, comprehensive Environmental Impact Statements (EIS). Large Language Model (LLM)s' effectiveness in specialized domains like NEPA remains untested for adoption in federal decision-making processes. To address this gap, we present NEPA Question and Answering Dataset (NEPAQuAD), the first comprehensive benchmark derived from EIS documents, along with a modular and transparent evaluation pipeline, MAPLE, to assess LLM performance on NEPA-focused regulatory reasoning tasks. Our benchmark leverages actual EIS documents to create diverse question types, ranging from factual to complex problem-solving ones. We built a modular and transparent evaluation pipeline to test both closed- and open-source models in zero-shot or context-driven QA benchmarks. We evaluate five state-of-the-art LLMs using our framework to assess both their prior knowledge and their ability to process NEPA-specific information. The experimental results reveal that all the models consistently achieve their highest performance when provided with the gold passage as context. While comparing the other context-driven approaches for each model, Retrieval Augmented Generation (RAG)-based approaches substantially outperform PDF document contexts, indicating that neither model is well suited for long-context question-answering tasks. Our analysis suggests that NEPA-focused regulatory reasoning tasks pose a significant challenge for LLMs, particularly in terms of understanding the complex semantics and effectively processing the lengthy regulatory documents.

Sai Munikoti, Deepesh Agarwal, Laya Das et al.

Deep reinforcement learning (DRL) has empowered a variety of artificial intelligence fields, including pattern recognition, robotics, recommendation-systems, and gaming. Similarly, graph neural networks (GNN) have also demonstrated their superior performance in supervised learning for graph-structured data. In recent times, the fusion of GNN with DRL for graph-structured environments has attracted a lot of attention. This paper provides a comprehensive review of these hybrid works. These works can be classified into two categories: (1) algorithmic enhancement, where DRL and GNN complement each other for better utility; (2) application-specific enhancement, where DRL and GNN support each other. This fusion effectively addresses various complex problems in engineering and life sciences. Based on the review, we further analyze the applicability and benefits of fusing these two domains, especially in terms of increasing generalizability and reducing computational complexity. Finally, the key challenges in integrating DRL and GNN, and potential future research directions are highlighted, which will be of interest to the broader machine learning community.

Sridevi Wagle, Sai Munikoti, Anurag Acharya et al.

Large language models (LLMs) have shown remarkable achievements in natural language processing tasks, producing high-quality outputs. However, LLMs still exhibit limitations, including the generation of factually incorrect information. In safety-critical applications, it is important to assess the confidence of LLM-generated content to make informed decisions. Retrieval Augmented Language Models (RALMs) is relatively a new area of research in NLP. RALMs offer potential benefits for scientific NLP tasks, as retrieved documents, can serve as evidence to support model-generated content. This inclusion of evidence enhances trustworthiness, as users can verify and explore the retrieved documents to validate model outputs. Quantifying uncertainty in RALM generations further improves trustworthiness, with retrieved text and confidence scores contributing to a comprehensive and reliable model for scientific applications. However, there is limited to no research on UQ for RALMs, particularly in scientific contexts. This study aims to address this gap by conducting a comprehensive evaluation of UQ in RALMs, focusing on scientific tasks. This research investigates how uncertainty scores vary when scientific knowledge is incorporated as pretraining and retrieval data and explores the relationship between uncertainty scores and the accuracy of model-generated outputs. We observe that an existing RALM finetuned with scientific knowledge as the retrieval data tends to be more confident in generating predictions compared to the model pretrained only with scientific knowledge. We also found that RALMs are overconfident in their predictions, making inaccurate predictions more confidently than accurate ones. Scientific knowledge provided either as pretraining or retrieval corpus does not help alleviate this issue. We released our code, data and dashboards at https://github.com/pnnl/EXPERT2.

Sameera Horawalavithana, Sai Munikoti, Ian Stewart et al.

Instruction finetuning is a popular paradigm to align large language models (LLM) with human intent. Despite its popularity, this idea is less explored in improving the LLMs to align existing foundation models with scientific disciplines, concepts and goals. In this work, we present SciTune as a tuning framework to improve the ability of LLMs to follow scientific multimodal instructions. To test our methodology, we use a human-generated scientific instruction tuning dataset and train a large multimodal model LLaMA-SciTune that connects a vision encoder and LLM for science-focused visual and language understanding. In comparison to the models that are finetuned with machine generated data only, LLaMA-SciTune surpasses human performance on average and in many sub-categories on the ScienceQA benchmark.

Sai Munikoti, Balasubramaniam Natarajan, Mahantesh Halappanavar

Influence maximization (IM) is a combinatorial problem of identifying a subset of nodes called the seed nodes in a network (graph), which when activated, provide a maximal spread of influence in the network for a given diffusion model and a budget for seed set size. IM has numerous applications such as viral marketing, epidemic control, sensor placement and other network-related tasks. However, the uses are limited due to the computational complexity of current algorithms. Recently, learning heuristics for IM have been explored to ease the computational burden. However, there are serious limitations in current approaches such as: (1) IM formulations only consider influence via spread and ignore self activation; (2) scalability to large graphs; (3) generalizability across graph families; (4) low computational efficiency with a large running time to identify seed sets for every test network. In this work, we address each of these limitations through a unique approach that involves (1) formulating a generic IM problem as a Markov decision process that handles both intrinsic and influence activations; (2) employing double Q learning to estimate seed nodes; (3) ensuring scalability via sub-graph based representations; and (4) incorporating generalizability via meta-learning across graph families. Extensive experiments are carried out in various standard networks to validate performance of the proposed Graph Meta Reinforcement learning (GraMeR) framework. The results indicate that GraMeR is multiple orders faster and generic than conventional approaches.

Sai Munikoti, Ian Stewart, Chengping Chai et al.

The application of generalist multimodal models (GMMs) to specialized scientific domains remains limited due to the scarcity of comprehensive domain-specific datasets that integrate multiple data modalities beyond text and images. In seismology, understanding earthquake phenomena requires the synthesis of timeseries waveform data, geographical imagery, and contextual metadata, a multimodal integration absent in existing seismic datasets. We present MultiSeismo, a large scale structured multimodal seismic dataset, comprising over 16K seismic events spanning 13 years (2010 to 2023) across diverse geographical regions. Each event data integrates waveform recordings from global station networks, intensity maps, population exposure visualizations, and a comprehensive textual description within a standardized JSON format. We additionally develop MISCE, a multimodal instruction set on top of raw data to enable supervised training and evaluation of GMMs on seismic reasoning tasks ranging from basic information retrieval to complex cross modal analysis. We leverage MISCE to finetune an existing multimodal model (Unified IO 2) enhanced with a specialized timeseries encoder, which yields SeisModal, the first domain specific multimodal model for comprehensive seismic analysis. Evaluation of state of the art multimodal models on MultiSeismo reveals significant challenges, particularly with time-series data processing for general purpose models, while demonstrating SeisModal's superior performance on seismic multimodal reasoning tasks. These results prove that MultiSeismo provides a rigorous benchmark for future multimodal research in seismology and validate the success of our domain specific architectural adaptations.

Rounak Meyur, Hung Phan, Sridevi Wagle et al.

Wind energy project assessments present significant challenges for decision-makers, who must navigate and synthesize hundreds of pages of environmental and scientific documentation. These documents often span different regions and project scales, covering multiple domains of expertise. This process traditionally demands immense time and specialized knowledge from decision-makers. The advent of Large Language Models (LLM) and Retrieval Augmented Generation (RAG) approaches offer a transformative solution, enabling rapid, accurate cross-document information retrieval and synthesis. As the landscape of Natural Language Processing (NLP) and text generation continues to evolve, benchmarking becomes essential to evaluate and compare the performance of different RAG-based LLMs. In this paper, we present a comprehensive framework to generate a domain relevant RAG benchmark. Our framework is based on automatic question-answer generation with Human (domain experts)-AI (LLM) teaming. As a case study, we demonstrate the framework by introducing WeQA, a first-of-its-kind benchmark on the wind energy domain which comprises of multiple scientific documents/reports related to environmental aspects of wind energy projects. Our framework systematically evaluates RAG performance using diverse metrics and multiple question types with varying complexity level, providing a foundation for rigorous assessment of RAG-based systems in complex scientific domains and enabling researchers to identify areas for improvement in domain-specific applications.

Sai Munikoti, Deepesh Agarwal, Laya Das et al.

Graph Neural Networks (GNN) provide a powerful framework that elegantly integrates Graph theory with Machine learning for modeling and analysis of networked data. We consider the problem of quantifying the uncertainty in predictions of GNN stemming from modeling errors and measurement uncertainty. We consider aleatoric uncertainty in the form of probabilistic links and noise in feature vector of nodes, while epistemic uncertainty is incorporated via a probability distribution over the model parameters. We propose a unified approach to treat both sources of uncertainty in a Bayesian framework, where Assumed Density Filtering is used to quantify aleatoric uncertainty and Monte Carlo dropout captures uncertainty in model parameters. Finally, the two sources of uncertainty are aggregated to estimate the total uncertainty in predictions of a GNN. Results in the real-world datasets demonstrate that the Bayesian model performs at par with a frequentist model and provides additional information about predictions uncertainty that are sensitive to uncertainties in the data and model.

Sai Munikoti, Anurag Acharya, Sridevi Wagle et al.

Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context from external knowledge sources to complement the language model. However, existing retrieval augmentation techniques ignore the structural relationships between these documents. Furthermore, retrieval models are not explored much in scientific tasks, especially in regard to the faithfulness of retrieved documents. In this paper, we propose a novel structure-aware retrieval augmented language model that accommodates document structure during retrieval augmentation. We create a heterogeneous document graph capturing multiple types of relationships (e.g., citation, co-authorship, etc.) that connect documents from more than 15 scientific disciplines (e.g., Physics, Medicine, Chemistry, etc.). We train a graph neural network on the curated document graph to act as a structural encoder for the corresponding passages retrieved during the model pretraining. Particularly, along with text embeddings of the retrieved passages, we obtain structural embeddings of the documents (passages) and fuse them together before feeding them to the language model. We evaluate our model extensively on various scientific benchmarks that include science question-answering and scientific document classification tasks. Experimental results demonstrate that structure-aware retrieval improves retrieving more coherent, faithful and contextually relevant passages, while showing a comparable performance in the overall accuracy.

Sai Munikoti, Anurag Acharya, Sridevi Wagle et al.

Despite the dramatic progress in Large Language Model (LLM) development, LLMs often provide seemingly plausible but not factual information, often referred to as hallucinations. Retrieval-augmented LLMs provide a non-parametric approach to solve these issues by retrieving relevant information from external data sources and augment the training process. These models help to trace evidence from an externally provided knowledge base allowing the model predictions to be better interpreted and verified. In this work, we critically evaluate these models in their ability to perform in scientific document reasoning tasks. To this end, we tuned multiple such model variants with science-focused instructions and evaluated them on a scientific document reasoning benchmark for the usefulness of the retrieved document passages. Our findings suggest that models justify predictions in science tasks with fabricated evidence and leveraging scientific corpus as pretraining data does not alleviate the risk of evidence fabrication.

Anurag Acharya, Sai Munikoti, Aaron Hellinger et al.

As LLMs have become increasingly popular, they have been used in almost every field. But as the application for LLMs expands from generic fields to narrow, focused science domains, there exists an ever-increasing gap in ways to evaluate their efficacy in those fields. For the benchmarks that do exist, a lot of them focus on questions that don't require proper understanding of the subject in question. In this paper, we present NuclearQA, a human-made benchmark of 100 questions to evaluate language models in the nuclear domain, consisting of a varying collection of questions that have been specifically designed by experts to test the abilities of language models. We detail our approach and show how the mix of several types of questions makes our benchmark uniquely capable of evaluating models in the nuclear domain. We also present our own evaluation metric for assessing LLM's performances due to the limitations of existing ones. Our experiments on state-of-the-art models suggest that even the best LLMs perform less than satisfactorily on our benchmark, demonstrating the scientific knowledge gap of existing LLMs.

Shweta Dahale, Sai Munikoti, Balasubramaniam Natarajan

Uncertainty quantification is a critical yet unsolved challenge for deep learning, especially for the time series imputation with irregularly sampled measurements. To tackle this problem, we propose a novel framework based on the principles of recurrent neural networks and neural stochastic differential equations for reconciling irregularly sampled measurements. We impute measurements at any arbitrary timescale and quantify the uncertainty in the imputations in a principled manner. Specifically, we derive analytical expressions for quantifying and propagating the epistemic and aleatoric uncertainty across time instants. Our experiments on the IEEE 37 bus test distribution system reveal that our framework can outperform state-of-the-art uncertainty quantification approaches for time-series data imputations.

Sameera Horawalavithana, Lauren Phillips, Ian Stewart et al.

Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and generalization, there is a pressing need to efficiently update existing VLMs to incorporate these advancements. However, the integration of new LLMs into VLMs, particularly how the evolving LLMs contribute to multimodal reasoning, alignment, and task-specific performance remains underexplored. Addressing this gap is important for VLM development, given the rapid evolution of pretrained LLM backbones. This study presents a controlled and systematic investigation of how changes in the pretrained LLM backbone affect downstream VLM task performance. By having the vision encoder, training data, and post-training algorithm remain same across LLAMA-1, LLAMA-2, and LLAMA-3 based VLMs, we find that newer LLM backbones do not always lead to better VLMs, but the performance depends on the downstream VLM task. For example, in visual question and answering tasks, newer LLM backbones tend to solve different questions rather than just more questions, and our analysis shows this is driven by differences in how the models process information, including better calibrated confidence and more stable internal representations. We also find that some VLM capabilities appear only in the newest LLM generation, while tasks that depend mainly on visual understanding see little benefit from a newer LLM backbone.

Ian Stewart, Sameera Horawalavithana, Brendan Kennedy et al.

Multimodal foundation models (MFMs) such as OFASys show the potential to unlock analysis of complex data such as images, videos, and audio data via text prompts alone. However, their performance may suffer in the face of text input that differs even slightly from their training distribution, which is surprising considering the use of modality-specific data to "ground" the text input. This study demonstrates that prompt instability is a major concern for MFMs, leading to a consistent drop in performance across all modalities, but that instability can be mitigated with additional training with augmented data. We evaluate several methods for grounded prompt perturbation, where we generate perturbations and filter based on similarity to text and/or modality data. After re-training the models on the augmented data, we find improved accuracy and more stable performance on the perturbed test data regardless of perturbation condition, suggesting that the data augmentation strategy helps the models handle domain shifts more effectively. In error analysis, we find consistent patterns of performance improvement across domains, suggesting that retraining on prompt perturbations tends to help general reasoning capabilities in MFMs.

Priyanka Gautam, Balasubramaniam Natarajan, Sai Munikoti et al.

In an age where information spreads rapidly across social media, effectively identifying influential nodes in dynamic networks is critical. Traditional influence maximization strategies often fail to keep up with rapidly evolving relationships and structures, leading to missed opportunities and inefficiencies. To address this, we propose a novel learning-based approach integrating Graph Neural Networks (GNNs) with Bidirectional Long Short-Term Memory (BiLSTM) models. This hybrid framework captures both structural and temporal dynamics, enabling accurate prediction of candidate nodes for seed set selection. The bidirectional nature of BiLSTM allows our model to analyze patterns from both past and future network states, ensuring adaptability to changes over time. By dynamically adapting to graph evolution at each time snapshot, our approach improves seed set calculation efficiency, achieving an average of 90% accuracy in predicting potential seed nodes across diverse networks. This significantly reduces computational overhead by optimizing the number of nodes evaluated for seed selection. Our method is particularly effective in fields like viral marketing and social network analysis, where understanding temporal dynamics is crucial.

Reilly Raab, Mike Parker, Dan Nally et al.

The advent of language models (LMs) has the potential to dramatically accelerate tasks that may be cast to text-processing; however, real-world adoption is hindered by concerns regarding safety, explainability, and bias. How can we responsibly leverage LMs in a transparent, auditable manner -- minimizing risk and allowing human experts to focus on informed decision-making rather than data-processing or prompt engineering? In this work, we propose a framework for declaring statically typed, LM-powered subroutines (i.e., callable, function-like procedures) for use within conventional asynchronous code -- such that sparse feedback from human experts is used to improve the performance of each subroutine online (i.e., during use). In our implementation, all LM-produced artifacts (i.e., prompts, inputs, outputs, and data-dependencies) are recorded and exposed to audit on demand. We package this framework as a library to support its adoption and continued development. While this framework may be applicable across several real-world decision workflows (e.g., in healthcare and legal fields), we evaluate it in the context of public comment processing as mandated by the 1969 National Environmental Protection Act (NEPA): Specifically, we use this framework to develop "CommentNEPA," an application that compiles, organizes, and summarizes a corpus of public commentary submitted in response to a project requiring environmental review. We quantitatively evaluate the application by comparing its outputs (when operating without human feedback) to historical ``ground-truth'' data as labelled by human annotators during the preparation of official environmental impact statements.

Sarthak Chaturvedi, Anurag Acharya, Rounak Meyur et al.

Evaluation benchmark characteristics may distort the true benefits of domain adaptation in retrieval models. This creates misleading assessments that influence deployment decisions in specialized domains. We show that two benchmarks with drastically different features such as topic diversity, boundary overlap, and semantic complexity can influence the perceived benefits of fine-tuning. Using environmental regulatory document retrieval as a case study, we fine-tune ColBERTv2 model on Environmental Impact Statements (EIS) from federal agencies. We evaluate these models across two benchmarks with different semantic structures. Our findings reveal that identical domain adaptation approaches show very different perceived benefits depending on evaluation methodology. On one benchmark, with clearly separated topic boundaries, domain adaptation shows small improvements (maximum 0.61% NDCG gain). However, on the other benchmark with overlapping semantic structures, the same models demonstrate large improvements (up to 2.22% NDCG gain), a 3.6-fold difference in the performance benefit. We compare these benchmarks through topic diversity metrics, finding that the higher-performing benchmark shows 11% higher average cosine distances between contexts and 23% lower silhouette scores, directly contributing to the observed performance difference. These results demonstrate that benchmark selection strongly determines assessments of retrieval system effectiveness in specialized domains. Evaluation frameworks with well-separated topics regularly underestimate domain adaptation benefits, while those with overlapping semantic boundaries reveal improvements that better reflect real-world regulatory document complexity. Our findings have important implications for developing and deploying AI systems for interdisciplinary domains that integrate multiple topics.

Sai Munikoti, Ian Stewart, Sameera Horawalavithana et al.

Multimodal models are expected to be a critical component to future advances in artificial intelligence. This field is starting to grow rapidly with a surge of new design elements motivated by the success of foundation models in natural language processing (NLP) and vision. It is widely hoped that further extending the foundation models to multiple modalities (e.g., text, image, video, sensor, time series, graph, etc.) will ultimately lead to generalist multimodal models, i.e. one model across different data modalities and tasks. However, there is little research that systematically analyzes recent multimodal models (particularly the ones that work beyond text and vision) with respect to the underling architecture proposed. Therefore, this work provides a fresh perspective on generalist multimodal models (GMMs) via a novel architecture and training configuration specific taxonomy. This includes factors such as Unifiability, Modularity, and Adaptability that are pertinent and essential to the wide adoption and application of GMMs. The review further highlights key challenges and prospects for the field and guide the researchers into the new advancements.

Laya Das, Sai Munikoti, Nrushad Joshi et al.

We study the problem of learning features through self-supervision that are generalisable to multiple graphs. State-of-the-art graph self-supervision restricts training to only one graph, resulting in graph-specific models that are incompatible with different but related graphs. We hypothesize that training with more than one graph that belong to the same family can improve the quality of the learnt representations. However, learning universal features from disparate node/edge features in different graphs is non-trivial. To address this challenge, we first homogenise the disparate features with graph-specific encoders that transform the features into a common space. A universal representation learning module then learns generalisable features on this common space. We show that compared to traditional self-supervision with one graph, our approach results in (1) better performance on downstream node classification, (2) learning features that can be re-used for unseen graphs of the same family, (3) more efficient training and (4) compact yet generalisable models. We also show ability of the proposed framework to deliver these benefits for relatively larger graphs. In this paper, we present a principled way to design foundation graph models that learn from more than one graph in an end-to-end manner, while bridging the gap between self-supervised and supervised performance.

Sai Munikoti, Laya Das, Balasubramaniam Natarajan

In the quest to improve efficiency, interdependence and complexity are becoming defining characteristics of modern complex networks representing engineered and natural systems. Graph theory is a widely used framework for modeling such complex networks and to evaluate their robustness to disruptions. Particularly, identification of critical nodes/links in a graph can facilitate the enhancement of graph (system) robustness and characterize crucial factors of system performance. Most existing methods of critical node identification are based on an iterative approach that explores each node/link of a graph. These methods suffer from high computational complexity and the resulting analysis is network specific. Additionally, uncertainty associated with the underlying graphical model further limits the potential value of these traditional approaches. To overcome these challenges, we propose a Bayesian graph neural network based node classification framework that is computationally efficient and systematically incorporates uncertainties. Instead of utilizing the observed graph for training the model, a MAP estimate of the graph is computed based on the observed topology and node target labels. Further, a Monte-Carlo (MC) dropout algorithm is incorporated to account for the epistemic uncertainty. The fidelity and the gain in computational complexity offered by the Bayesian framework is illustrated using simulation results.

Sai Munikoti, Laya Das, Balasubramaniam Natarajan

Identifying critical nodes and links in graphs is a crucial task. These nodes/links typically represent critical elements/communication links that play a key role in a system's performance. However, a majority of the methods available in the literature on the identification of critical nodes/links are based on an iterative approach that explores each node/link of a graph at a time, repeating for all nodes/links in the graph. Such methods suffer from high computational complexity and the resulting analysis is also network-specific. To overcome these challenges, this article proposes a scalable and generic graph neural network (GNN) based framework for identifying critical nodes/links in large complex networks. The proposed framework defines a GNN based model that learns the node/link criticality score on a small representative subset of nodes/links. An appropriately trained model can be employed to predict the scores of unseen nodes/links in large graphs and consequently identify the most critical ones. The scalability of the framework is demonstrated through prediction of nodes/links scores in large scale synthetic and real-world networks. The proposed approach is fairly accurate in approximating the criticality scores and offers a significant computational advantage over conventional approaches.