adaptive-testing

Adaptive Testing Framework for AI Models (Psychometrics in AI Evaluation)

Adapting Questions to the student ability

Completely free, browser-based mockups of the HireVue's Cognitive Assessment tasks.

Score Impact Analyzer is a data-driven tool that simulates Digital SAT adaptive scoring to identify which missed questions have the highest impact on a student’s final score, helping optimize study focus for maximum improvement.

Research-grade adaptive capability profiling for autonomous AI agents using multidimensional IRT and information gain.

This project considers the use of p-value weighting to voxel-based lesion behavior mapping (VLSM) studies. Our methods are demonstrated on an aphasia study investigating which regions of the brain are associated with the severity of language impairment among stroke survivors.

Item Response Theory (IRT) — the framework behind adaptive tests like GRE and PTE. Designed for AI engineers and data scientists to grasp core IRT concepts for adaptive testing systems.

AI-powered adaptive IQ assessment platform featuring cognitive analysis, age-group calibration, skill-level profiling, adaptive difficulty adjustment, and multi-domain intelligence evaluation.

1D Adaptive Testing Engine using Item Response Theory (IRT) | FastAPI · MongoDB Atlas · GPT-4o-mini | Dynamically adjusts GRE question difficulty based on real-time ability estimation

1D adaptive diagnostic engine, uses item response theory (Rasch Model) to dynamically select GRE - style questions based on student ability then generates a pesonalized AI study plan.

IRT-based adaptive testing engine with real-time question selection

An adaptive testing backend built with FastAPI and MongoDB that dynamically adjusts question difficulty based on student performance and generates personalized study recommendations.

SmartTest — a Computerized Adaptive Testing (CAT) web app in PHP/MySQL where question difficulty adapts to candidate skill in real time

Rank LLMs with a fraction of the benchmark items, same ranking — adaptive (IRT/CAT) evaluation as a small, zero-dependency, drop-in Python library. The nanoGPT of adaptive LLM eval.

Adaptive forced-choice Big Five assessment with AI-driven scoring and 1,015,342-response calibration. Live: https://billzi2016.github.io/tirt-ocean-quiz/

Adaptive GRE prep tool using 1PL IRT with Fisher Information item selection for real-time ability estimation. LLM generates personalized study plans with curated resources. Built with FastAPI, MongoDB Atlas, Clerk Auth, and OpenRouter. 74 tests, Docker support, structured logging.

Adaptive AI skill assessment: one AI-graded written warm-up, then an adaptive MCQ staircase from pre-generated banks. AI does the language work, deterministic TypeScript owns every number.

Evidence-first test orchestration for Web, games, and authorized security exploration with adaptive replay, HATE/v1 artifacts, and external QEG gates.

AI-powered adaptive testing engine using FastAPI, MongoDB, and IRT-based difficulty adjustment.

Verifiable AI model evaluation — adaptive psychometric measurement with tamper-evident, Bitcoin-anchored results. Working paper + proof of concept.