Aayush Kumar

Aayush Kumar, Jimiama Mafeni Mase, Divish Rengasamy et al.

This paper presents an open-source Python toolbox called Ensemble Feature Importance (EFI) to provide machine learning (ML) researchers, domain experts, and decision makers with robust and accurate feature importance quantification and more reliable mechanistic interpretation of feature importance for prediction problems using fuzzy sets. The toolkit was developed to address uncertainties in feature importance quantification and lack of trustworthy feature importance interpretation due to the diverse availability of machine learning algorithms, feature importance calculation methods, and dataset dependencies. EFI merges results from multiple machine learning models with different feature importance calculation approaches using data bootstrapping and decision fusion techniques, such as mean, majority voting and fuzzy logic. The main attributes of the EFI toolbox are: (i) automatic optimisation of ML algorithms, (ii) automatic computation of a set of feature importance coefficients from optimised ML algorithms and feature importance calculation techniques, (iii) automatic aggregation of importance coefficients using multiple decision fusion techniques, and (iv) fuzzy membership functions that show the importance of each feature to the prediction task. The key modules and functions of the toolbox are described, and a simple example of their application is presented using the popular Iris dataset.

Jenny T. Liang, Aayush Kumar, Yasharth Bajpai et al. · microsoft-research

Spreadsheet programming is challenging. Programmers use spreadsheet programming knowledge (e.g., formulas) and problem-solving skills to combine actions into complex tasks. Advancements in large language models have introduced language agents that observe, plan, and perform tasks, showing promise for spreadsheet creation. We present TableTalk, a spreadsheet programming agent embodying three design principles -- scaffolding, flexibility, and incrementality -- derived from studies with seven spreadsheet programmers and 85 Excel templates. TableTalk guides programmers through structured plans based on professional workflows, generating three potential next steps to adapt plans to programmer needs. It uses pre-defined tools to generate spreadsheet components and incrementally build spreadsheets. In a study with 20 programmers, TableTalk produced higher-quality spreadsheets 2.3 times more likely to be preferred than the baseline. It reduced cognitive load and thinking time by 12.6%. From this, we derive design guidelines for agentic spreadsheet programming tools and discuss implications on spreadsheet programming, end-user programming, AI-assisted programming, and human-agent collaboration.

Aayush Kumar, Daniel Prol, Amin Alipour et al.

LLMs such as ChatGPT have been widely adopted by students in higher education as tools for learning programming and related concepts. However, it remains unclear how effective students are and what strategies students use while learning with LLMs. Since the majority of students' experiences in online self-learning have come through using search engines such as Google, evaluating AI tools in this context can help us address these gaps. In this mixed methods research, we conducted an exploratory within-subjects study to understand how CS2 students learn programming concepts using both LLMs as well as traditional online methods such as educational websites and videos to examine how students approach learning within and across both scenarios. We discovered that students found it easier to learn a more difficult concept using traditional methods than using ChatGPT. We also found that students ask fewer follow-ups and use more keyword-based queries for search engines while their prompts to LLMs tend to explicitly ask for information.

Aayush Kumar

Hallucinations hinder reliable question answering, especially in resource-constrained deployments where frontier-scale models or retrieval pipelines may be impractical. We present EdgeJury, a lightweight ensemble framework that improves truthfulness and robustness using only small instruction-tuned language models (3B-8B) suitable for serverless edge inference. EdgeJury orchestrates four stages: (1) parallel role-specialized generation, (2) anonymized cross-review with structured critiques and rankings, (3) chairman synthesis that integrates the strongest content while addressing flagged issues, and (4) claim-level consistency labeling based on inter-model agreement. On TruthfulQA (MC1), EdgeJury achieves 76.2% accuracy (95% CI: 72.8-79.6%), a +21.4% relative improvement over a single 8B baseline (62.8%), and outperforms standard baselines including self-consistency and majority voting under transparent compute accounting (total tokens and platform cost reported). On a 200-question adversarial EdgeCases set, EdgeJury yields +48.2% relative gains (95% CI: 44.0-52.4%). Manual analysis on 100 incorrect answers shows an approximately 55% reduction in factual hallucination errors versus the single-model baseline. Deployed on Cloudflare Workers AI, EdgeJury achieves 8.4 s median end-to-end latency, demonstrating that coordinated small-model ensembles can improve truthfulness on misconception-heavy QA benchmarks without external retrieval or proprietary large-model APIs.

Nikita Mehrotra, Aayush Kumar, Sumit Gulwani et al.

We present a neurosymbolic approach, TEN, for extracting tabular data from semistructured input text. This task is particularly challenging for text input that does not use special delimiters consistently to separate columns and rows. Purely neural approaches perform poorly due to hallucinations and their inability to enforce hard constraints. TEN uses Structural Decomposition prompting - a specialized chain-of-thought prompting approach - on a large language model (LLM) to generate an initial table, and thereafter uses a symbolic checker to evaluate not only the well-formedness of that table, but also detect cases of hallucinations or forgetting. The output of the symbolic checker is processed by a critique-LLM to generate guidance for fixing the table, which is presented to the original LLM in a self-debug loop. Our extensive experiments demonstrate that TEN significantly outperforms purely neural baselines across multiple datasets and metrics, achieving significantly higher exact match accuracy and substantially reduced hallucination rates. A 21-participant user study further confirms that TEN's tables are rated significantly more accurate (mean score: 5.0 vs 4.3; p = 0.021), and are consistently preferred for ease of verification and correction, with participants favoring our method in over 60% of the cases.

Aayush Kumar, Sanat B Singh, Suresh Chandra Satapathy et al.

Malaria is considered one of the deadliest diseases in today world which causes thousands of deaths per year. The parasites responsible for malaria are scientifically known as Plasmodium which infects the red blood cells in human beings. The parasites are transmitted by a female class of mosquitos known as Anopheles. The diagnosis of malaria requires identification and manual counting of parasitized cells by medical practitioners in microscopic blood smears. Due to the unavailability of resources, its diagnostic accuracy is largely affected by large scale screening. State of the art Computer-aided diagnostic techniques based on deep learning algorithms such as CNNs, with end to end feature extraction and classification, have widely contributed to various image recognition tasks. In this paper, we evaluate the performance of custom made convnet Mosquito-Net, to classify the infected and uninfected cells for malaria diagnosis which could be deployed on the edge and mobile devices owing to its fewer parameters and less computation power. Therefore, it can be wildly preferred for diagnosis in remote and countryside areas where there is a lack of medical facilities.