Author name cluster

Vipul Gupta

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

TMLR Journal 2025 Journal Article

Improving Consistency in Large Language Models through Chain of Guidance

Harsh Raj
Vipul Gupta
Domenic Rosati
Subhabrata Majumdar

Consistency is a fundamental dimension of trustworthiness in Large Language Models (LLMs). For humans to be able to trust LLM-based applications, their outputs should be consistent when prompted with inputs that carry the same meaning or intent. Despite this need, there is no known mechanism to control and guide LLMs to be more consistent at inference time. In this paper, we introduce a novel alignment strategy to maximize semantic consistency in LLM outputs. Our proposal is based on \textbf{Chain of Guidance} (CoG), a multistep prompting technique that generates highly consistent outputs from LLMs. For closed-book question-answering (Q\&A) tasks, when compared to direct prompting, the outputs generated using CoG show improved consistency. While other approaches like template-based responses and majority voting may offer alternative paths to consistency, our work focuses on exploring the potential of guided prompting. We use synthetic data sets comprised of consistent input-output pairs to fine-tune LLMs to produce consistent {\it and} correct outputs. Our fine-tuned models are more than twice as consistent compared to base models and show strong generalization capabilities by producing consistent outputs over datasets not used in the fine-tuning process. Code is available at \url{https://github.com/vijilAI/chain_of_guidance}.

PDF Details

EAAI Journal 2025 Journal Article

Interpretable multi-source data fusion through Latent Variable Gaussian Process

Sandipp Krishnan Ravi
Yigitcan Comlek
Arjun Pathak
Vipul Gupta
Rajnikant Umretiya
Andrew Hoffman
Ghanshyam Pilania
Piyush Pandita

With the advent of artificial intelligence and machine learning, various domains of science and engineering communities have leveraged data-driven surrogates to model complex systems through fusing numerous sources of information (data) from published papers, patents, open repositories, or other available resources. However, very little attention has been paid to the differences in quality and comprehensiveness of the known and unknown underlying physical parameters of the information sources, which could have downstream implications during system optimization. Towards resolving this issue, an interpretable multi-source data fusion framework based on Latent Variable Gaussian Process (LVGP) model is proposed. The individual data sources are first labeled as categorical variables and then mapped into a physically meaningful latent space, enabling the development of a source-aware data fusion model. Additionally, a dissimilarity metric based on the learned latent variables of the LVGP is introduced to study and understand the differences between the data sources. The proposed approach is demonstrated on and analyzed through two mathematical and two materials engineering case studies. From the case studies, it is observed that the proposed multi-source data fusion framework provides more accurate predictions for sparse data scenarios compared to single-source or source-unaware data fusion models.

Details DOI

NeurIPS Conference 2024 Conference Paper

Consent in Crisis: The Rapid Decline of the AI Data Commons

Shayne Longpre
Robert Mahari
Ariel Lee
Campbell Lund
Hamidah Oderinwale
William Brannon
Nayan Saxena
Naana Obeng-Marnu

General-purpose artificial intelligence (AI) systems are built on massive swathes of public web data, assembled into corpora such as C4, RefinedWeb, and Dolma. To our knowledge, we conduct the first, large-scale, longitudinal audit of the consent protocols for the web domains underlying AI training corpora. Our audit of 14, 000 web domains provides an expansive view of crawlable web data and how codified data use preferences are changing over time. We observe a proliferation of AI-specific clauses to limit use, acute differences in restrictions on AI developers, as well as general inconsistencies between websites' expressed intentions in their Terms of Service and their robots. txt. We diagnose these as symptoms of ineffective web protocols, not designed to cope with the widespread re-purposing of the internet for AI. Our longitudinal analyses show that in a single year (2023-2024) there has been a rapid crescendo of data restrictions from web sources, rendering ~5\%+ of all tokens in C4, or 28%+ of the most actively maintained, critical sources in C4, fully restricted from use. For Terms of Service crawling restrictions, a full 45% of C4 is now restricted. If respected or enforced, these restrictions are rapidly biasing the diversity, freshness, and scaling laws for general-purpose AI systems. We hope to illustrate the emerging crises in data consent, for both developers and creators. The foreclosure of much of the open web will impact not only commercial AI, but also non-commercial AI and academic research.

PDF Details DOI

UAI Conference 2021 Conference Paper

LocalNewton: Reducing communication rounds for distributed learning

Vipul Gupta
Avishek Ghosh
Michal Derezinski
Rajiv Khanna
Kannan Ramchandran
Michael W. Mahoney

To address the communication bottleneck problem in distributed optimization within a master-worker framework, we propose LocalNewton, a distributed second-order algorithm with local averaging. In LocalNewton, the worker machines update their model in every iteration by finding a suitable second-order descent direction using only the data and model stored in their own local memory. We let the workers run multiple such iterations locally and communicate the models to the master node only once every few (say $L$) iterations. LocalNewton is highly practical since it requires only one hyperparameter, the number $L$ of local iterations. We use novel matrix concentration based techniques to obtain theoretical guarantees for LocalNewton, and we validate them with detailed empirical evaluation. To enhance practicability, we devise an adaptive scheme to choose $L$, and we show that this reduces the number of local iterations in worker machines between two model synchronizations as the training proceeds, successively refining the model quality at the master. Via extensive experiments using several real-world datasets with AWS Lambda workers and an AWS EC2 master, we show that LocalNewton requires fewer than $60%$ of the communication rounds (between master and workers) and less than $40%$ of the end-to-end running time, compared to state-of-the-art algorithms, to reach the same training loss.

Details

ICLR Conference 2020 Conference Paper

Stochastic Weight Averaging in Parallel: Large-Batch Training That Generalizes Well

Vipul Gupta
Santiago Akle Serrano
Dennis DeCoste

We propose Stochastic Weight Averaging in Parallel (SWAP), an algorithm to accelerate DNN training. Our algorithm uses large mini-batches to compute an approximate solution quickly and then refines it by averaging the weights of multiple models computed independently and in parallel. The resulting models generalize equally well as those trained with small mini-batches but are produced in a substantially shorter time. We demonstrate the reduction in training time and the good generalization performance of the resulting models on the computer vision datasets CIFAR10, CIFAR100, and ImageNet.

Details