Explanipedia

Exposing AI Bias by Crowdsourcing: Democratizing Critique of Large Language Models Open

Hangzhi Guo, Pranav Narayanan Venkit, Eunchae Jang, Mukund Srinath, Wenbo Zhang , et al. · 2025

The widespread adoption of large language models (LLMs) and generative AI (GenAI) tools across diverse real-world applications has amplified the importance of addressing societal biases inherent within these technologies. While the Natural…

Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing Open

Vishnu Asutosh Dasu, Md Rafi ur Rashid, Vipul Gupta, Saeid Tizpaz-Niari, Gang Tan · 2025

This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitive social contexts where fairness concerns become especially…

Interpretable multi-source data fusion through Latent Variable Gaussian Process Open

Sandipp Krishnan Ravi, Yigitcan Comlek, Arjun K. Pathak, Vipul Gupta, Rajnikant V. Umretiya , et al. · 2025

Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet Open

Berk Atil, Vipul Gupta, Sarkar Snigdha Sarathi Das, Rebecca J. Passonneau · 2025

Large language models (LLMs) have become ubiquitous, thus it is important to understand their risks and limitations. Smaller LLMs can be deployed where compute resources are constrained, such as edge devices, but with different propensity …

The Impact of Advertising on Consumers Perception Open

Sonali sankhla, Akshay Katiyar, Vipul Gupta · 2024

Now-a-days marketing is the need of the hour. It can be defined as a tool for the different companies those who want to attract and influence the customers’ perception. In today’s society consumers have intense powers on the other hand mar…

The Influence of Online Reviews on Consumer Learning and Purchase Decisions Open

Sonali sankhla, Akshay Katiyar, Vipul Gupta · 2024

The proliferation of online reviews has significantly altered consumer behavior, impacting both learning processes and purchase decisions. This paper investigates how online reviews shape consumer perceptions and decision-making. By synthe…

Hey GPT, Can You be More Racist? Analysis from Crowdsourced Attempts to Elicit Biased Content from Generative AI Open

Hangzhi Guo, Pranav Narayanan Venkit, Eunchae Jang, Mukund Srinath, Wenbo Zhang , et al. · 2024

The widespread adoption of large language models (LLMs) and generative AI (GenAI) tools across diverse applications has amplified the importance of addressing societal biases inherent within these technologies. While the NLP community has …

Expansion of the neocortex and protection from neurodegeneration by in vivo transient reprogramming Open

Yiru Shen, Sofía Zaballa, Xavier Bech, Anna Sancho‐Balsells, Irene Rodríguez-Navarro , et al. · 2024

Yamanaka factors (YFs) can reverse some aging features in mammalian tissues, but their effects on the brain remain largely unexplored. Here, we induced YFs in the mouse brain in a controlled spatiotemporal manner in two different scenarios…

Corrosion behavior of additively manufactured FeCrAl in out-of-pile light water reactor environments Open

Rajnikant V. Umretiya, Haozheng J. Qu, Liang Yin, Timothy B. Jurewicz, Vipul Gupta , et al. · 2024

Iron-Chromium-Aluminum (FeCrAl) alloys are candidate materials for the cladding of light water reactor (LWR) fuels. The FeCrAl alloys in general range in Cr composition from 12% (C26M) to 21% (APMT). In this work, the general corrosion beh…

Changing Answer Order Can Decrease MMLU Accuracy Open

Vipul Gupta, David Pantoja, Candace Ross, Adina Williams, Megan Ung · 2024

As large language models (LLMs) have grown in prevalence, particular benchmarks have become essential for the evaluation of these models and for understanding model capabilities. Most commonly, we use test accuracy averaged across multiple…

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing Open

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu , et al. · 2024

This work is motivated by two key trends. On one hand, large language models (LLMs) have shown remarkable versatility in various generative tasks such as writing, drawing, and question answering, significantly reducing the time required fo…

Corrosion behavior of additively manufactured FeCrAl in out-of-pile light water reactor environments Open

Raúl B. Rebak, Rajnikant V. Umretiya, Haozheng J. Qu, Liang Yin, Timothy B. Jurewicz , et al. · 2024

Iron-Chromium-Aluminum (FeCrAl) alloys are candidate materials for the cladding of Light Water Reactor (LWR) fuels. The FeCrAl alloys in general range in Cr composition from 12% (C26M) to 21% (APMT). In this work the general corrosion beha…

An Audit on the Perspectives and Challenges of Hallucinations in NLP Open

Pranav Narayanan Venkit, Tatiana Chakravorti, Vipul Gupta, Heidi Biggs, Mukund Srinath , et al. · 2024

We audit how hallucination in large language models (LLMs) is characterized in peer-reviewed literature, using a critical examination of 103 publications across NLP research. Through the examination of the literature, we identify a lack of…

Semantics-Enabled Data Federation: Bringing Materials Scientists Closer to FAIR Data Open

Kareem S. Aggour, Vijay S. Kumar, Vipul Gupta, Alfredo Gabaldon, Paul Cuddihy , et al. · 2024

The development and discovery of new materials can be significantly enhanced through the adoption of FAIR (Findable, Accessible, Interoperable, and Reusable) data principles and the establishment of a robust data infrastructure in support …

Challenges in Adopting Industry 4.0 for Indian Automobile Industries: A Key Experts’ Perspective Open

Mohammad Faisal Noor, Amaresh Kumar, Shubham Tripathi, Vipul Gupta · 2024

Industry 4.0 has revolutionised manufacturing, presenting significant challenges for adoption, particularly in developing countries like India.This study identifies and evaluates challenges specific to the Indian automobile industry's impl…

Interpretable Multi-Source Data Fusion Through Latent Variable Gaussian Process Open

Sandipp Krishnan Ravi, Yigitcan Comlek, Wei Chen, Arjun K. Pathak, Vipul Gupta , et al. · 2024

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) fr…

The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis Open

Pranav Narayanan Venkit, Mukund Srinath, Sanjana Gautam, Saranya Venkatraman, Vipul Gupta , et al. · 2023

We conduct an inquiry into the sociotechnical aspects of sentiment analysis (SA) by critically examining 189 peer-reviewed papers on their applications, models, and datasets. Our investigation stems from the recognition that SA has become …

CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias Open

Vipul Gupta, Pranav Narayanan Venkit, Hugo Laurençon, Shomir Wilson, Rebecca J. Passonneau · 2023

As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to c…

Sociodemographic Bias in Language Models: A Survey and Forward Path Open

Vipul Gupta, Pranav Narayanan Venkit, Shomir Wilson, Rebecca J. Passonneau · 2023

Sociodemographic bias in language models (LMs) has the potential for harm when deployed in real-world settings. This paper presents a comprehensive survey of the past decade of research on sociodemographic bias in LMs, organized into a typ…

Do we need entire training data for adversarial training? Open

Vipul Gupta, Apurva Narayan · 2023

Deep Neural Networks (DNNs) are being used to solve a wide range of problems in many domains including safety-critical domains like self-driving cars and medical imagery. DNNs suffer from vulnerability against adversarial attacks. In the p…

Optimizing chemistry for designing oxidation resistant FeCrAl alloys Open

Indranil Roy, Hamdy Abouelella, Rajnikant V. Umretiya, Subhrajit Roychowdhury, Bojun Feng , et al. · 2023

Data-driven predictive modeling of FeCrAl oxidation Open

Indranil Roy, Subhrajit Roychowdhury, Bojun Feng, Sandipp Krishnan Ravi, Sayan Ghosh , et al. · 2023

The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis Open

Pranav Narayanan Venkit, Mukund Srinath, Sanjana Gautam, Saranya Venkatraman, Vipul Gupta , et al. · 2023

Pranav Venkit, Mukund Srinath, Sanjana Gautam, Saranya Venkatraman, Vipul Gupta, Rebecca Passonneau, Shomir Wilson. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Damage Accumulations Predictions for Boiler Components Via Microstructurally Informed Material Models Open

Monica Soare, Vipul Gupta, Reddy Ganta, M. Karadge, Chen Shen · 2022

The goal of the project was to model material behavior and degradation during cyclic plasticity— with and without hold time—for nickel-based superalloys used in USC (ultra-super-critical) and A-USC (advanced-ultra-super-critical) boiler co…

Understanding Impacts of Chemistry on Oxidation of FeCrAl Alloys Open

Indranil Roy, Hamdy Abouelella, Rajnikant V. Umretiya, Subhrajit Roychowdhury, Bojun Feng , et al. · 2022

Traditionally, FeCrAl alloys played an important role in high-temperature applications due to their ability to form a passive Al oxide film at temperatures above ~800°C. Recently, FeCrAl alloys became of interest for the application of acc…

SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering Open

Vipul Gupta, Zhuowan Li, Adam Kortylewski, Chenyu Zhang, Yingwei Li , et al. · 2022

While Visual Question Answering (VQA) has progressed rapidly, previous works raise concerns about robustness of current VQA models. In this work, we study the robustness of VQA models from a novel perspective: visual context. We suggest th…

Oxidation Resistance in 1200°C Steam of a FeCrAl Alloy Fabricated by Three Metallurgical Processes Open

Andrew Hoffman, Rajnikant V. Umretiya, Vipul Gupta, Michael Due Larsen, Corey Graff , et al. · 2022

Advanced Characterization Techniques Enabling Commercial Development of Accident Tolerant Fuel Cladding Open

Andrew Hoffman, Vipul Gupta, Michael Due Larsen, Soumya Nag, Ian Spinelli , et al. · 2021

An abstract is not available for this content so a preview has been provided. As you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Role of corporate responsibility for ensuring social and environmental sustainability in an emerging economy like India Open

Vipul Gupta, Nishi Sharma, Mandeep Kaur, M.Siraji, Neetu Jain , et al. · 2021

The rapid industrialization and urbanization over the previous decades has resulted in an increase in growth of population. This increase in business and industrialization are the fundamental sources of development, employment and improved…

BEAR: Sketching BFGS Algorithm for Ultra-High Dimensional Feature\n Selection in Sublinear Memory Open

Amirali Aghazadeh, Vipul Gupta, Alex DeWeese, O. Ozan Koyluoglu, Kannan Ramchandran · 2020

We consider feature selection for applications in machine learning where the\ndimensionality of the data is so large that it exceeds the working memory of\nthe (local) computing machine. Unfortunately, current large-scale sketching\nalgori…

Vipul Gupta YOU? Author Swipe