Automating Risk-of-Bias Assessments with Gemini
Manual research synthesis is slow and prone to error. Learn how cumulative prompting and strict JSON validation create a robust pipeline for studies.
Best quote from Automating Risk-of-Bias Assessments with Gemini
The script is essentially building a specialized expert out of a general-purpose model, one layer of context at a time, by providing a total environment—a sandbox of information—to ensure the highest possible chance of a valid, scientifically useful response.
This audio lesson was created by a BeFreed community member
https://github.com/carljuneau/scaiences/blob/master/studies%2Fllm-rob%2Fsrc%2Frun_models.py
Frequently Asked Questions
Cumulative prompting is a method of building an AI's context in stages, where each subsequent level of instruction retains all previous information while adding new, more complex layers. In this specific script, the process is divided into four conditions: Condition A provides the baseline study and ID; Condition B adds a specific JSON schema and risk-of-bias criteria; Condition C introduces "training material" or methodological textbooks; and Condition D adds a "worked example" featuring a completed assessment of a separate study to serve as a gold-standard reference for the model.
The script employs a "guilty until proven innocent" approach to AI responses through a strict validation gate. After the model generates a response, the script parses the JSON to ensure it matches the required schema and verifies that the study_id in the output matches the input study to prevent hallucinations. Furthermore, the script requires the AI to provide a "verbatim quote" from the PDF for every judgment made, forcing the model to anchor its scientific claims in the actual text of the study.
The PROMPT_BRIDGE is a specific string used as a linguistic marker to help the model transition from reading training materials or examples to performing the actual task on the target study, which is crucial for maintaining focus in long-context windows. Setting the temperature to zero ensures the model's output is deterministic and consistent rather than creative. In a research context, this "boring" consistency is preferred because it prioritizes accuracy and reproducibility over varied or "fun" responses.
The script uses a robust two-strike system for errors. If a response fails to parse or validate on the first attempt, the script logs the error and automatically tries a second time. If it fails again, the script records the failure in a detailed CSV log (parse_failures.csv) including the study ID, model used, and the specific error message. This allows researchers to audit the process and identify if certain models or prompts are consistently struggling with specific types of data.
The PromptAssetResolver is a dynamic discovery tool that allows the script to find necessary files—like training PDFs or example JSONs—without the researcher having to hardcode every file path. It uses a scoring system to search through directories for keywords like "mulder" or "green" to identify the best-fit materials for the prompt. This makes the script flexible and portable, allowing different researchers to use the same logic even if their file naming conventions vary slightly, while still "failing loudly" if it finds ambiguous or conflicting files.
Discover more
High-Speed Academic Information Synthesis
In an era of information overload, the ability to quickly distill peer-reviewed research is a critical competitive advantage. This plan is designed for researchers, students, and lifelong learners who need to master complex subjects without succumbing to cognitive burnout.
Gemini and Homey Pro Intelligence
This plan is essential for smart home enthusiasts and developers looking to move beyond static routines into the era of generative AI. It bridges the gap between powerful LLMs and physical hardware, making it ideal for those seeking to build a more responsive and intelligent home ecosystem.
Automate Your Daily Data Gruntwork
Data-heavy roles often lose hours to manual entry and cleaning, leading to burnout and errors. This plan is designed for professionals who want to leverage AI and automation to handle high-volume document processing and data standardization with minimal effort.
How Gemma Sees the World
As multimodal AI becomes the industry standard, understanding the transition from hybrid to unified architectures is essential for developers. This plan is ideal for AI engineers and researchers looking to master how Gemma processes visual data without traditional separate encoders.
Teach Psych with AI-Resistant Assessments
As generative AI reshapes academia, psychology educators must evolve their pedagogical approach to ensure genuine student mastery. This plan is designed for instructors and professors who want to combine science-based teaching methods with innovative assessment strategies that prioritize human critical thinking over automated outputs.
The Skeptic's Guide to Causal Genomics
This guide is essential for bioinformaticians and researchers who need to move beyond simple correlation to identify true disease drivers. It provides the critical toolkit necessary to navigate the complexities of TWAS and confounding variables in modern regulatory networks.
The Ethical UX Researcher's AI Playbook
As AI reshapes research, maintaining integrity is paramount for UX professionals. This playbook is designed for researchers and product designers who need to balance rapid innovation with data dignity and rigorous output governance.
Synthesize research on the science of romance
This plan bridges the gap between biological drive and psychological behavior to decode the complexities of human intimacy. It is ideal for researchers, psychology students, or anyone seeking a data-driven understanding of how we form and maintain romantic bonds.
From Columbia University alumni built in San Francisco
"Instead of endless scrolling, I just hit play on BeFreed. It saves me so much time."
"I never knew where to start with nonfiction—BeFreed’s book lists turned into podcasts gave me a clear path."
"Perfect balance between learning and entertainment. Finished ‘Thinking, Fast and Slow’ on my commute this week."
"Crazy how much I learned while walking the dog. BeFreed = small habits → big gains."
"Reading used to feel like a chore. Now it’s just part of my lifestyle."
"Feels effortless compared to reading. I’ve finished 6 books this month already."
"BeFreed turned my guilty doomscrolling into something that feels productive and inspiring."
"BeFreed turned my commute into learning time. 20-min podcasts are perfect for finishing books I never had time for."
"BeFreed replaced my podcast queue. Imagine Spotify for books — that’s it. 🙌"
"It is great for me to learn something from the book without reading it."
"The themed book list podcasts help me connect ideas across authors—like a guided audio journey."
"Makes me feel smarter every time before going to work"
From Columbia University alumni built in San Francisco
"Instead of endless scrolling, I just hit play on BeFreed. It saves me so much time."
"I never knew where to start with nonfiction—BeFreed’s book lists turned into podcasts gave me a clear path."
"Perfect balance between learning and entertainment. Finished ‘Thinking, Fast and Slow’ on my commute this week."
"Crazy how much I learned while walking the dog. BeFreed = small habits → big gains."
"Reading used to feel like a chore. Now it’s just part of my lifestyle."
"Feels effortless compared to reading. I’ve finished 6 books this month already."
"BeFreed turned my guilty doomscrolling into something that feels productive and inspiring."
"BeFreed turned my commute into learning time. 20-min podcasts are perfect for finishing books I never had time for."
"BeFreed replaced my podcast queue. Imagine Spotify for books — that’s it. 🙌"
"It is great for me to learn something from the book without reading it."
"The themed book list podcasts help me connect ideas across authors—like a guided audio journey."
"Makes me feel smarter every time before going to work"
"Instead of endless scrolling, I just hit play on BeFreed. It saves me so much time."
"I never knew where to start with nonfiction—BeFreed’s book lists turned into podcasts gave me a clear path."
"Perfect balance between learning and entertainment. Finished ‘Thinking, Fast and Slow’ on my commute this week."
"Crazy how much I learned while walking the dog. BeFreed = small habits → big gains."
"Reading used to feel like a chore. Now it’s just part of my lifestyle."
"Feels effortless compared to reading. I’ve finished 6 books this month already."
"BeFreed turned my guilty doomscrolling into something that feels productive and inspiring."
"BeFreed turned my commute into learning time. 20-min podcasts are perfect for finishing books I never had time for."
"BeFreed replaced my podcast queue. Imagine Spotify for books — that’s it. 🙌"
"It is great for me to learn something from the book without reading it."
"The themed book list podcasts help me connect ideas across authors—like a guided audio journey."
"Makes me feel smarter every time before going to work"
"Instead of endless scrolling, I just hit play on BeFreed. It saves me so much time."
"I never knew where to start with nonfiction—BeFreed’s book lists turned into podcasts gave me a clear path."
"Perfect balance between learning and entertainment. Finished ‘Thinking, Fast and Slow’ on my commute this week."
"Crazy how much I learned while walking the dog. BeFreed = small habits → big gains."
"Reading used to feel like a chore. Now it’s just part of my lifestyle."
"Feels effortless compared to reading. I’ve finished 6 books this month already."
"BeFreed turned my guilty doomscrolling into something that feels productive and inspiring."
"BeFreed turned my commute into learning time. 20-min podcasts are perfect for finishing books I never had time for."
"BeFreed replaced my podcast queue. Imagine Spotify for books — that’s it. 🙌"
"It is great for me to learn something from the book without reading it."
"The themed book list podcasts help me connect ideas across authors—like a guided audio journey."
"Makes me feel smarter every time before going to work"
