Working with biomedical corpora often requires programming skills, specialised formats, and time-consuming preprocessing. But what if you could transform a complex annotated dataset—like the NCBI Disease Corpus—into a structured, analysis-ready CSV using nothing more than a single, well-designed prompt? In this post, we demonstrate how a no-code, GenAI-powered
Large language models (LLMs) rely on a set of parameters that directly influence how text is generated — affecting randomness, repetition, length, and coherence. Understanding of these parameters is essential when working with LLMs in research, application development, or evaluation settings. While chat-based interfaces such as ChatGPT, Copilot, or Gemini typically
As generative AI technologies continue to transform the research landscape, major academic publishers are beginning to integrate AI-powered tools directly into their platforms. These tools aim to support researchers at various stages of the scientific workflow – from literature discovery and summarisation to writing assistance and experimental comparison. This article provides
Having previously explored the FutureHouse Platform’s agents in tasks such as identifying tailor-made laws and generating a literature review on legislative backsliding, we now directly compare its Falcon agent and OpenAI’s o3. Our aim was to assess their performance on a focused literature search task: compiling a ranked
In recent years, Retrieval-Augmented Generation (RAG) has emerged as a powerful method for enhancing large language models with structured access to external document collections. By combining dense semantic search with contextual text generation, RAG systems have proven particularly useful for tasks such as answering questions based on extensive documentation, enabling
Navigating Horizon Europe’s 2025 Work Programme means dealing with twelve separate documents, each several hundred pages long. These include funding calls, eligibility conditions, strategic priorities, and legal annexes—making it difficult to locate critical information quickly. To address this challenge, poltextLAB developed a domain-specific Custom GPT (Horizon Navigator '
Can a large language model accurately solve a university-level microeconomics exercise on health insurance? We tested Manus AI on a multi-part problem involving demand curves, list prices, out-of-pocket prices, and the calculation of social loss under various insurance schemes – including full insurance, coinsurance, and copayment plans. Not only did the
In our earlier posts, we explored how useful existing Custom GPTs are for academic tasks and explained how to create your own GPT from scratch. This follow-up post puts those insights into practice by introducing QuantiCheck—a Custom GPT we developed specifically to assess the methodological rigour and reproducibility of
In our previous blog post, we examined how useful publicly available Custom GPTs are for academic tasks. While many showed promise, especially for brainstorming or outlining, they often fell short in areas where accuracy, source verification, and methodological transparency are crucial. In short: if your work demands high standards of
In this post, we present a straightforward yet revealing task: classifying 25 philosophical and scientific arguments as either deductive or inductive. We tested Mistral Le Chat on this argument classification task to evaluate its ability to distinguish between these fundamental forms of reasoning. Le Chat demonstrated a solid grasp of
Thematic content analysis is a key method in political text interpretation, but it typically requires human judgement to define categories and trace meaning. In this study, we explored whether Grok 3, a state-of-the-art large language model, can carry out this task autonomously—without predefined themes or external guidance. Using Martin
Can a language model accurately classify argumentative claims without any prior examples or fine-tuning? We put DeepSeek-V3 to the test on a real-world stance classification task involving 200 claims from a structured dataset. The model was asked to determine, for each claim, whether it supported (PRO) or opposed (CON) a
