MétaCan
Menu
Back to cohort
Record W4405601028 · doi:10.1109/icsme58944.2024.00075

Developing a Llama-Based Chatbot for CI/CD Question Answering: A Case Study at Ericsson

2024· article· en· W4405601028 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAI in Service Interactions
Canadian institutionsEricsson (Canada)University of Ottawa
Fundersnot available
KeywordsChatbotComputer scienceQuestion answeringWorld Wide WebNatural language processing

Abstract

fetched live from OpenAlex

This paper presents our experience developing a Llama-based chatbot for question answering about continuous integration and continuous delivery (CI/CD) at Ericsson, a multinational telecommunications company. Our chatbot is designed to handle the specificities of CI/CD documents at Ericsson, employing a retrieval-augmented generation (RAG) model to enhance accuracy and relevance. Our empirical evaluation of the chatbot on industrial CI/CD-related questions indicates that an ensemble retriever, combining BM25 and embedding retrievers, yields the best performance. When evaluated against a ground truth of 72 CI/CD questions and answers at Ericsson, our most accurate chatbot configuration provides fully correct answers for 61.11% of the questions, partially correct answers for 26.39%, and incorrect answers for 12.50%. Through an error analysis of the partially correct and incorrect answers, we discuss the underlying causes of inaccuracies and provide insights for further refinement. We also reflect on lessons learned and suggest future directions for further improving our chatbot's accuracy.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.949
Threshold uncertainty score0.565

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.060
GPT teacher head0.370
Teacher spread0.310 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations14
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicAI in Service InteractionsFrench-language works237,207