Raquib Bin Yousuf

Raquib Bin Yousuf

Auto-generated profile, based on publicly available information

Raquib Bin Yousuf

Virginia Tech Virginia USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 March 2026
Verified
Book Chapter
Closed access
PDF file
RYRaquib Bin Yousuf
Raquib Bin Yousuf
SXShengzhe Xu
Shengzhe Xu
MSMandar Sharma
Mandar Sharma
ANAndrew Neeser
Andrew Neeser
CLChris Latimer
Chris Latimer
NRNaren Ramakrishnan
Naren Ramakrishnan

17 January 2026 in arXiv
Verified
Preprint
Open access
PDF file
RYRaquib Bin Yousuf
Raquib Bin Yousuf
SXShengzhe Xu
Shengzhe Xu
MSMandar Sharma
Mandar Sharma
ANAndrew Neeser
Andrew Neeser
CLChris Latimer
Chris Latimer
NRNaren Ramakrishnan
Naren Ramakrishnan
Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk similarity alone often fails to distinguish between documents with overlapping language. Practitioners often flatten metadata into input text as a heuristic, but the impact and trade-offs of this practice remain poorly understood. We present a systematic study of metadata-aware retrieval strategies, comparing plain-text baselines with approaches that embed metadata directly. Our evaluation spans metadata-as-text (prefix and suffix), a dual-encoder unified embedding that fuses metadata and content in a single index, dual-encoder late-fusion retrieval, and metadata-aware query reformulation. Across multiple retrieval metrics and question types, we find that prefixing and unified embeddings consistently outperform plain-text baselines, with the unified at times exceeding prefixing while being easier to maintain. Beyond empirical comparisons, we analyze embedding space, showing that metadata integration improves effectiveness by increasing intra-document cohesion, reducing inter-document confusion, and widening the separation between relevant and irrelevant chunks. Field-level ablations show that structural cues provide strong disambiguating signals. Our code, evaluation framework, and the RAGMATE-10K dataset are publicly hosted.

25 November 2024 in arXiv
Verified
Preprint
Open access
PDF file
RYRaquib Bin Yousuf
Raquib Bin Yousuf
NDNicholas Defelice
Nicholas Defelice
MSMandar Sharma
Mandar Sharma
SXShengzhe Xu
Shengzhe Xu
NRNaren Ramakrishnan
Naren Ramakrishnan
Building on their demonstrated ability to perform a variety of tasks, we investigate the application of large language models (LLMs) to enhance in-depth analytical reasoning within the context of intelligence analysis. Intelligence analysts typically work with massive dossiers to draw connections between seemingly unrelated entities, and uncover adversaries' plans and motives. We explore if and how LLMs can be helpful to analysts for this task and develop an architecture to augment the capabilities of an LLM with a memory module called dynamic evidence trees (DETs) to develop and track multiple investigation threads. Through extensive experiments on multiple datasets, we highlight how LLMs, as-is, are still inadequate to support intelligence analysts and offer recommendations to improve LLMs for such intricate reasoning applications.

3 August 2025
Verified
Conference Paper
Open access
SSShailik Sarkar
Shailik Sarkar
RYRaquib Bin Yousuf
Raquib Bin Yousuf
LWLinhan Wang
Linhan Wang
BMBrian Mayer
Brian Mayer
TMThomas Mortier
Thomas Mortier
NRNaren Ramakrishnan
Naren Ramakrishnan

4 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
RYRaquib Bin Yousuf
Raquib Bin Yousuf
AKAadyant Khatri
Aadyant Khatri
SXShengzhe Xu
Shengzhe Xu
MSMandar Sharma
Mandar Sharma
NRNaren Ramakrishnan
Naren Ramakrishnan
Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs). However, these benchmarks often rely on simplistic 'needle in a haystack' retrieval or continuation tasks that may not accurately reflect the performance of these models in information-dense scenarios. Thus, rather than simple next token prediction, we argue for evaluating these models on more complex reasoning tasks that requires them to induce structured relational knowledge from the text - such as graphs from potentially noisy natural language content. While the input text can be viewed as generated in terms of a graph, its structure is not made explicit and connections must be induced from distributed textual cues, separated by long contexts and interspersed with irrelevant information. Our findings reveal that LLMs begin to exhibit memory drift and contextual forgetting at much shorter effective lengths when tasked with this form of relational reasoning, compared to what existing benchmarks suggest. With these findings, we offer recommendations for the optimal use of popular LLMs for complex reasoning tasks. We further show that even models specialized for reasoning, such as OpenAI o1, remain vulnerable to early memory drift in these settings. These results point to significant limitations in the models' ability to abstract structured knowledge from unstructured input and highlight the need for architectural adaptations to improve long-range reasoning.