6 papers
When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
Mahdi Astaraki, Mohammad Arshi Saloot, Ali Shiraee Kasmaee +2
Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-reasoning loops meaningfully outpe…
Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study
Mohammad Khodadad, Ali Shiraee Kasmaee, Mahdi Astaraki +3
In this study, we introduced a new benchmark consisting of a curated dataset and a defined evaluation process to assess the compositional reasoning capabilities of large language m…
ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text Embeddings
Ali Shiraee Kasmaee, Mohammad Khodadad, Mehdi Astaraki +4
Retrieval-Augmented Generation (RAG) systems in chemistry heavily depend on accurate and relevant retrieval of chemical literature. However, general-purpose text embedding models f…
Mambular: A Sequential Model for Tabular Deep Learning
Anton Frederik Thielmann, Manish Kumar, Christoph Weisser +3
The analysis of tabular data has traditionally been dominated by gradient-boosted decision trees (GBDTs), known for their proficiency with mixed categorical and numerical features.…
ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain
Ali Shiraee Kasmaee, Mohammad Khodadad, Mohammad Arshi Saloot +4
Recent advancements in language models have started a new era of superior information retrieval and content generation, with embedding models playing an important role in optimizin…
On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning
Anton Frederik Thielmann, Soheila Samiee
Recent advancements in tabular deep learning (DL) have led to substantial performance improvements, surpassing the capabilities of traditional models. With the adoption of techniqu…