Domain-specific question answering remains challenging for language models, given the deep technical knowledge required to answer questions correctly. This difficulty is amplified for smaller language models that cannot encode as much information in their parameters as larger models. The "Specializing Large Language Models for Telecom Networks" challenge aimed to enhance the performance of two small language models, Phi-2 and Falcon-7B in telecommunication question answering. In this paper, we present our question answering systems for this challenge. Our solutions achieved leading marks of 81.9% accuracy for Phi-2 and 57.3% for Falcon-7B. We have publicly released our code and fine-tuned models.

翻译：针对特定领域的问答任务，由于需要深厚的专业知识才能正确回答问题，这对语言模型而言仍然具有挑战性。对于参数规模较小、无法像大型模型那样编码大量信息的语言模型而言，这一困难尤为突出。"面向电信网络的专业化大语言模型"挑战赛旨在提升Phi-2和Falcon-7B两款小型语言模型在电信领域问答任务中的性能。本文介绍了我们为该挑战赛开发的问答系统。我们的解决方案在Phi-2模型上取得了81.9%的领先准确率，在Falcon-7B模型上取得了57.3%的准确率。我们已公开了相关代码及微调后的模型。