As Large Language Models (LLMs) become more capable of handling increasingly complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely used in educational assessment, measures the ability of individual test items to differentiate between high and low performers. Inspired by this theory, we propose an ID-induced prompt synthesis framework for evaluating LLMs so that the evaluation set continually updates and refines according to model abilities. Our data synthesis framework prioritizes both breadth and specificity. It can generate prompts that comprehensively evaluate the capabilities of LLMs while revealing meaningful performance differences between models, allowing for effective discrimination of their relative strengths and weaknesses across various tasks and domains. To produce high-quality data, we incorporate a self-correct mechanism into our generalization framework and develop two models to predict prompt discrimination and difficulty score to facilitate our data synthesis framework, contributing valuable tools to evaluation data synthesis research. We apply our generated data to evaluate five SOTA models. Our data achieves an average score of 51.92, accompanied by a variance of 10.06. By contrast, previous works (i.e., SELF-INSTRUCT and WizardLM) obtain an average score exceeding 67, with a variance below 3.2. The results demonstrate that the data generated by our framework is more challenging and discriminative compared to previous works. We will release a dataset of over 3,000 carefully crafted prompts to facilitate evaluation research of LLMs.

Insect migration provides major ecosystem services, and sometimes, migratory pests cause serious crop damage and yield loss. Species identification is critically important in studies of insect migration, for both entomologists and pest managers. Radar is an effective means of detecting insect migrants. Current entomological radars usually operate at X-band, and signal amplitude information is used to estimate body mass and wing-beat frequency, which can then be used to categorize migratory insects into broad taxon classes. To improve the identification performance, this paper presents a novel radar method of measuring insect mass and body length. The multifrequency radar cross sections (RCS) of insects at X-band and Ku-/K-band are fully investigated, and the comprehensive relationship between RCS and insect morphological parameters provides an improvement in the estimation of insect mass. More importantly, estimations of body length can also be realized with an accuracy of 84% based on experimental data acquired by a vector network analyzer in a microwave anechoic chamber. If multifrequency RCS measurements can be obtained by radar in the future, then highly accurate estimations of insect mass and body length will be possible, although it is currently still a challenge to build a radar capable of making the required measurements over such a wide frequency range.