Hi, I'm Yash

In this work, we investigate two paradigms for citing sources in generated text: Generation Time Citation (G Cite) and Post hoc Citation (P Cite). G Cite annotates evidence as text is produced, whereas P Cite retrospectively links generated answers to retrieved documents. Through experiments on multiple attribution datasets we show that citation quality is largely governed by the quality of retrieval. P Cite yields higher coverage and competitive correctness compared to G Cite, which suggests that post hoc approaches can provide more complete attribution while remaining precise. Our analysis supports a retrieval centric, P Cite first strategy in high stakes domains, where transparency and completeness of citations are critical.

This paper benchmarks the consistency and reasoning abilities of large language models using the Boolq dataset. We assess both public and proprietary models using metrics such as BERT score, BLEU, and F1 on generated explanations and answers. Results show that proprietary models outperform open source alternatives, but no model excels at both consistency and reasoning at the same time. The findings highlight gaps in current evaluation practice and point to the need for models that can both reason and maintain internal consistency across tasks.

This work introduces MetamorphASM, a benchmark of 328,200 obfuscated assembly code snippets, to evaluate whether LLMs can generate obfuscated malware. We test models under various obfuscation techniques, including dead code insertion, register substitution, and control flow manipulation, and find that LLMs are capable of producing obfuscated code that challenges static analysis tools. The study emphasises the dual use nature of LLMs and calls for safeguards that can mitigate malicious applications.

This paper presents a sentiment driven machine learning pipeline for identifying the mental state of engineering students from social media posts. By combining sentiment analysis with recurrent neural networks (RNNs), gated recurrent units (GRUs), and support vector machines (SVMs), the system classifies emotions into categories such as anxiety, joy, and sadness. The approach aims to support early detection of mental health concerns and encourage proactive support in academic communities.