arXiv subjects

Nitisha Jain

Publications and source records attributed to Nitisha Jain.

8 recordsLinked to original sources

arXiv2025

Towards deployment-centric multimodal AI beyond vision and language

Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most multimodal AI advances focus on models for vision and language data, while their deployability remains a key challenge. We advocate a deployment-centric workflow that incorporates deployment constraints early to reduce the likelihood of undeployable solutions, complementing data-centric and model-centric approaches. We also emphasise deeper integration across multiple levels of multimodality and multidisciplinary collaboration to significantly broaden the research scope beyond vision and language. To facilitate this approach, we identify common multimodal-AI-specific challenges shared across disciplines and examine three real-world use cases: pandemic response, self-driving car design, and climate change adaptation, drawing expertise from healthcare, social science, engineering, science, sustainability, and finance. By fostering multidisciplinary dialogue and open research practices, our community can accelerate deployment-centric development for broad societal impact.

cs.AI↗

arXiv2024

Improving Ontology Requirements Engineering with OntoChat and Participatory Prompting

Past ontology requirements engineering (ORE) has primarily relied on manual methods, such as interviews and collaborative forums, to gather user requirements from domain experts, especially in large projects. Current OntoChat offers a framework for ORE that utilises large language models (LLMs) to streamline the process through four key functions: user story creation, competency question (CQ) extraction, CQ filtration and analysis, and ontology testing support. In OntoChat, users are expected to prompt the chatbot to generate user stories. However, preliminary evaluations revealed that they struggle to do this effectively. To address this issue, we experimented with a research method called participatory prompting, which involves researcher-mediated interactions to help users without deep knowledge of LLMs use the chatbot more effectively. This participatory prompting user study produces pre-defined prompt templates based on user queries, focusing on creating and refining personas, goals, scenarios, sample data, and data resources for user stories. These refined user stories will subsequently be converted into CQs.

cs.HC↗

arXiv2024

Talking Wikidata: Communication patterns and their impact on community engagement in collaborative knowledge graphs

We study collaboration patterns of Wikidata, one of the world's largest open source collaborative knowledge graph (KG) communities. Collaborative KG communities, play a key role in structuring machine-readable knowledge to support AI systems like conversational agents. However, these communities face challenges related to long-term member engagement, as a small subset of contributors often is responsible for the majority of contributions and decision-making. While prior research has explored contributors' roles and lifespans, discussions within collaborative KG communities remain understudied. To fill this gap, we investigated the behavioural patterns of contributors and factors affecting their communication and participation. We analysed all the discussions on Wikidata using a mixed methods approach, including statistical tests, network analysis, and text and graph embedding representations. Our findings reveal that the interactions between Wikidata editors form a small world network, resilient to dropouts and inclusive, where both the network topology and discussion content influence the continuity of conversations. Furthermore, the account age of Wikidata members and their conversations are significant factors in their long-term engagement with the project. Our observations and recommendations can benefit the Wikidata and semantic web communities, providing guidance on how to improve collaborative environments for sustainability, growth, and quality.

cs.SI↗

arXiv2024

A Standardized Machine-readable Dataset Documentation Format for Responsible AI

Data is critical to advancing AI technologies, yet its quality and documentation remain significant challenges, leading to adverse downstream effects (e.g., potential biases) in AI applications. This paper addresses these issues by introducing Croissant-RAI, a machine-readable metadata format designed to enhance the discoverability, interoperability, and trustworthiness of AI datasets. Croissant-RAI extends the Croissant metadata format and builds upon existing responsible AI (RAI) documentation frameworks, offering a standardized set of attributes and practices to facilitate community-wide adoption. Leveraging established web-publishing practices, such as Schema.org, Croissant-RAI enables dataset users to easily find and utilize RAI metadata regardless of the platform on which the datasets are published. Furthermore, it is seamlessly integrated into major data search engines, repositories, and machine learning frameworks, streamlining the reading and writing of responsible AI metadata within practitioners' existing workflows. Croissant-RAI was developed through a community-led effort. It has been designed to be adaptable to evolving documentation requirements and is supported by a Python library and a visual editor.

cs.IR↗

arXiv2024

Croissant: A Metadata Format for ML-Ready Datasets

Data is a critical resource for machine learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that creates a shared representation across ML tools, frameworks, and platforms. Croissant makes datasets more discoverable, portable, and interoperable, thereby addressing significant challenges in ML data management. Croissant is already supported by several popular dataset repositories, spanning hundreds of thousands of datasets, enabling easy loading into the most commonly-used ML frameworks, regardless of where the data is stored. Our initial evaluation by human raters shows that Croissant metadata is readable, understandable, complete, yet concise.

cs.LG↗

arXiv2023

Using Large Language Models for Knowledge Engineering (LLMKE): A Case Study on Wikidata

In this work, we explore the use of Large Language Models (LLMs) for knowledge engineering tasks in the context of the ISWC 2023 LM-KBC Challenge. For this task, given subject and relation pairs sourced from Wikidata, we utilize pre-trained LLMs to produce the relevant objects in string format and link them to their respective Wikidata QIDs. We developed a pipeline using LLMs for Knowledge Engineering (LLMKE), combining knowledge probing and Wikidata entity mapping. The method achieved a macro-averaged F1-score of 0.701 across the properties, with the scores varying from 1.00 to 0.328. These results demonstrate that the knowledge of LLMs varies significantly depending on the domain and that further experimentation is required to determine the circumstances under which LLMs can be used for automatic Knowledge Base (e.g., Wikidata) completion and correction. The investigation of the results also suggests the promising contribution of LLMs in collaborative knowledge engineering. LLMKE won Track 2 of the challenge. The implementation is available at https://github.com/bohuizhang/LLMKE.

cs.CL↗

arXiv2023

Agreeing and Disagreeing in Collaborative Knowledge Graph Construction: An Analysis of Wikidata

In this work, we study disagreements in discussions around Wikidata, an online knowledge community that builds the data backend of Wikipedia. Discussions are essential in collaborative work as they can increase contributor performance and encourage the emergence of shared norms and practices. While disagreements can play a productive role in discussions, they can also lead to conflicts and controversies, which impact contributor' well-being and their motivation to engage. We want to understand if and when such phenomena arise in Wikidata, using a mix of quantitative and qualitative analyses to identify the types of topics people disagree about, the most common patterns of interaction, and roles people play when arguing for or against an issue. We find that decisions to create Wikidata properties are much faster than those to delete properties and that more than half of controversial discussions do not lead to consensus. Our analysis suggests that Wikidata is an inclusive community, considering different opinions when making decisions, and that conflict and vandalism are rare in discussions. At the same time, while one-fourth of the editors participating in controversial discussions contribute legitimate and insightful opinions about Wikidata's emerging issues, they respond with one or two posts and do not remain engaged in the discussions to reach consensus. Our work contributes to the analysis of collaborative KG construction with insights about communication and decision-making in projects, as well as with methodological directions and open datasets. We hope our findings will help managers and designers support community decision-making and improve discussion tools and practices.

cs.HC↗

arXiv2022

Discovering Fine-Grained Semantics in Knowledge Graph Relations

When it comes to comprehending and analyzing multi-relational data, the semantics of relations are crucial. Polysemous relations between different types of entities, that represent multiple semantics, are common in real-world relational datasets represented by knowledge graphs. For numerous use cases, such as entity type classification, question answering and knowledge graph completion, the correct semantic interpretation of these relations is necessary. In this work, we provide a strategy for discovering the different semantics associated with abstract relations and deriving many sub-relations with fine-grained meaning. To do this, we leverage the types of the entities associated with the relations and cluster the vector representations of entities and relations. The suggested method is able to automatically discover the best number of sub-relations for a polysemous relation and determine their semantic interpretation, according to our empirical evaluation.

cs.AI↗