Breakthroughs, discoveries, and DIY tips sent every weekday. Archaeologists in Scotland have excavated over 100 weapon projectiles, including cannon shot and lead musket balls from one of the country's most famous battlefields . With these new finds, experts say they can better contextualize the Battle of Culloden, as well as highlight some of the conflict's lesser known participants. In July 1745, Charles Stuart arrived in Scotland seeking to return his father to the British throne. For the next nine months, Stuart proceeded to lead thousands of supporters, militiamen, and conscripted soldiers in a military campaign now known as the Jacobite rising of 1745 .

Math Word Problems (MWPs) are crucial for evaluating the capability of Large Language Models (LLMs), with current research primarily focusing on questions with concise contexts. However, as real-world math problems often involve complex circumstances, LLMs' ability to solve long MWPs is vital for their applications in these scenarios, yet remains under-explored. This study pioneers the exploration of Context Length Generalizability (CoLeG), the ability of LLMs to solve long MWPs. We introduce Extended Grade-School Math (E-GSM), a collection of MWPs with lengthy narratives. Two novel metrics are proposed to assess the efficacy and resilience of LLMs in solving these problems. Our examination of existing zero-shot prompting techniques and both proprietary and open-source LLMs reveals a general deficiency in CoLeG. To alleviate these challenges, we propose distinct approaches for different categories of LLMs. For proprietary LLMs, a new instructional prompt is proposed to mitigate the influence of long context. For open-source LLMs, a new data augmentation task is developed to improve CoLeG. Our comprehensive results demonstrate the effectiveness of our proposed methods, showing not only improved performance on E-GSM but also generalizability across several other MWP benchmarks. Our findings pave the way for future research in employing LLMs for complex, real-world applications, offering practical solutions to current limitations and opening avenues for further exploration of model generalizability and training methodologies.

Large language models show compelling performance on reasoning tasks but they tend to perform much worse in languages other than English. This is unsurprising given that their training data largely consists of English text and instructions. A typical solution is to translate instruction data into all languages of interest, and then train on the resulting multilingual data, which is called translate-training. This approach not only incurs high cost, but also results in poorly translated data due to the non-standard formatting of chain-of-thought and mathematical reasoning instructions. In this paper, we explore the benefits of question alignment, where we train the model to translate reasoning questions into English by finetuning on X-English question data. In this way we perform targetted, in-domain language alignment which makes best use of English instruction data to unlock the LLMs' multilingual reasoning abilities. Experimental results on LLaMA2-13B show that question alignment leads to consistent improvements over the translate-training approach: an average improvement of 11.3\% and 16.1\% accuracy across ten languages on the MGSM and MSVAMP maths reasoning benchmarks (The project will be available at: https://github.com/NJUNLP/QAlign).

It's the little moments that get you. Skeletal oak trees lining starkly frozen meadows. It is very strange to play a modern big-budget video game and to be taken back to childhood memories, to places that feel somehow imprinted on the psyche. In this way, Forza Horizon 4, the latest open-world driving sim from Leamington Spa-based developer Playground Games, may be the most emotional racing game I've ever played. Since the arrival of the first title in the series six years ago, each Horizon has featured a densely detailed, near photo-realistic reproduction of real-world geography.