ColBERT Retrieval and Ensemble Response Scoring for Language Model Question Answering
This work addresses the problem of improving question answering accuracy in telecom for smaller language models, but it is incremental as it applies existing retrieval and scoring methods to a new domain.
The paper tackled domain-specific question answering for telecom networks by enhancing small language models Phi-2 and Falcon-7B, achieving accuracies of 81.9% and 57.3% respectively.
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.