Raquib Bin Yousuf

Raquib Bin Yousuf, Subhodip Biswas, Kulendra Kumar Kaushal et al.

Understanding key insights from full-text scholarly articles is essential as it enables us to determine interesting trends, give insight into the research and development, and build knowledge graphs. However, some of the interesting key insights are only available when considering full-text. Although researchers have made significant progress in information extraction from short documents, extraction of scientific entities from full-text scholarly literature remains a challenging problem. This work presents an automated End-to-end Research Entity Extractor called EneRex to extract technical facets such as dataset usage, objective task, method from full-text scholarly research articles. Additionally, we extracted three novel facets, e.g., links to source code, computing resources, programming language/libraries from full-text articles. We demonstrate how EneRex is able to extract key insights and trends from a large-scale dataset in the domain of computer science. We further test our pipeline on multiple datasets and found that the EneRex improves upon a state of the art model. We highlight how the existing datasets are limited in their capacity and how EneRex may fit into an existing knowledge graph. We also present a detailed discussion with pointers for future research. Our code and data are publicly available at https://github.com/DiscoveryAnalyticsCenter/EneRex.

Raquib Bin Yousuf, Nicholas Defelice, Mandar Sharma et al.

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.

Raquib Bin Yousuf, Aadyant Khatri, Shengzhe Xu et al.

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.

Shailik Sarkar, Raquib Bin Yousuf, Linhan Wang et al.

Illegal logging poses a significant threat to global biodiversity, climate stability, and depresses international prices for legal wood harvesting and responsible forest products trade, affecting livelihoods and communities across the globe. Stable isotope ratio analysis (SIRA) is rapidly becoming an important tool for determining the harvest location of traded, organic, products. The spatial pattern in stable isotope ratio values depends on factors such as atmospheric and environmental conditions and can thus be used for geographic origin identification. We present here the results of a deployed machine learning pipeline where we leverage both isotope values and atmospheric variables to determine timber harvest location. Additionally, the pipeline incorporates uncertainty estimation to facilitate the interpretation of harvest location determination for analysts. We present our experiments on a collection of oak (Quercus spp.) tree samples from its global range. Our pipeline outperforms comparable state-of-the-art models determining geographic harvest origin of commercially traded wood products, and has been used by European enforcement agencies to identify harvest location misrepresentation. We also identify opportunities for further advancement of our framework and how it can be generalized to help identify the origin of falsely labeled organic products throughout the supply chain.

Shengzhe Xu, Cho-Ting Lee, Mandar Sharma et al.

Synthetic data generation is integral to ML pipelines, e.g., to augment training data, replace sensitive information, and even to power advanced platforms like DeepSeek. While LLMs fine-tuned for synthetic data generation are gaining traction, synthetic table generation -- a critical data type in business and science -- remains under-explored compared to text and image synthesis. This paper shows that LLMs, whether used as-is or after traditional fine-tuning, are inadequate for generating synthetic tables. Their autoregressive nature, combined with random order permutation during fine-tuning, hampers the modeling of functional dependencies and prevents capturing conditional mixtures of distributions essential for real-world constraints. We demonstrate that making LLMs permutation-aware can mitigate these issues.