SciDA: Scientific Dynamic Assessor of LLMs

Advancement in Large Language Models (LLMs) reasoning capabilities enables them to solve scientific problems with enhanced efficacy. Thereby, a high-quality benchmark for comprehensive and appropriate assessment holds significance, while existing ones either confront the risk of data contamination or lack involved disciplines. To be specific, due to the data source overlap of LLMs training and static benchmark, the keys or number pattern of answers inadvertently memorized (i.e. data contamination), leading to systematic overestimation of their reasoning capabilities, especially numerical reasoning. We propose SciDA, a multidisciplinary benchmark that consists exclusively of over 1k Olympic-level numerical computation problems, allowing randomized numerical initializations for each inference round to avoid reliance on fixed numerical patterns. We conduct a series of experiments with both closed-source and open-source top-performing LLMs, and it is observed that the performance of LLMs drop significantly under random numerical initialization. Thus, we provide truthful and unbiased assessments of the numerical reasoning capabilities of LLMs. The data is available at https://huggingface.co/datasets/m-a-p/SciDA

Traffic Prediction with Transfer Learning: A Mutual Information-based Approach

In modern traffic management, one of the most essential yet challenging tasks is accurately and timely predicting traffic. It has been well investigated and examined that deep learning-based Spatio-temporal models have an edge when exploiting Spatio-temporal relationships in traffic data. Typically, data-driven models require vast volumes of data, but gathering data in small cities can be difficult owing to constraints such as equipment deployment and maintenance costs. To resolve this problem, we propose TrafficTL, a cross-city traffic prediction approach that uses big data from other cities to aid data-scarce cities in traffic prediction. Utilizing a periodicity-based transfer paradigm, it identifies data similarity and reduces negative transfer caused by the disparity between two data distributions from distant cities. In addition, the suggested method employs graph reconstruction techniques to rectify defects in data from small data cities. TrafficTL is evaluated by comprehensive case studies on three real-world datasets and outperforms the state-of-the-art baseline by around 8 to 25 percent.