基于ColBERT检索和集成响应评分的语言模型问答系统
ColBERT Retrieval and Ensemble Response Scoring for Language Model Question Answering
AI总结：
本文提出基于ColBERT检索和集成响应评分的方法，提升小语言模型在电信领域问答任务中的性能，Phi-2模型达到81.9%准确率，Falcon-7B模型达到57.3%准确率。
摘要：
领域特定的问题回答仍对语言模型来说具有挑战性，因为需要深入的技术知识来正确回答问题。这种困难在较小的语言模型中尤为明显，因为它们无法像较大的模型那样在参数中编码大量信息。'专门化大型语言模型用于电信网络'挑战旨在增强两个小型语言模型Phi-2和Falcon-7B在电信问题回答任务中的性能。在本文中，我们提出了针对此挑战的问题回答系统。我们的解决方案在Phi-2上达到了81.9%的准确率，在Falcon-7B上达到了57.3%的准确率。我们已公开发布了我们的代码和微调模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
