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.
@article{arxiv.2408.10808,
title = {ColBERT Retrieval and Ensemble Response Scoring for Language Model Question Answering},
author = {Alex Gichamba and Tewodros Kederalah Idris and Brian Ebiyau and Eric Nyberg and Teruko Mitamura},
journal= {arXiv preprint arXiv:2408.10808},
year = {2024}
}
Comments
7 pages, 2 figures, and 8 tables. This paper has been accepted at the 2024 IEEE Global Communications (GLOBECOM) Workshops