MétaCan
Menu
Back to cohort

Developing A Chatbot: A Hybrid Approach Using Deep Learning and RAG

2024· article· en· W4410087685 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.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAI in Service Interactions
Canadian institutionsMcMaster UniversityLakehead University
FundersLakehead University
KeywordsChatbotComputer scienceDeep learningArtificial intelligenceHuman–computer interactionNatural language processing

Abstract

fetched live from OpenAlex

The rapid growth of online shopping has underscored the need for effective customer service techniques that go beyond traditional channels such as email, mobile responses, and FAQs. In this dynamic landscape, chatbots have emerged as indispensable tools for enhancing customer satisfaction and streamlining consumer interactions. These artificial intelligence-powered chatbots are reshaping the online retail industry by providing human-like engagement. Our study introduces a hybrid approach to developing a context-aware chatbot. We combine intent recognition using deep learning models with a retrieval-based argument approach, leveraging OpenAI's Large Language Model (LLM). Specifically, we compare two intent recognition models: LSTM and BERT. Additionally, we implement a retriever system that gathers relevant supporting data from a vector database storing the vector embeddings of our products. The outcome is a dynamic and customer-centric chatbot experience that harnesses the capabilities of OpenAI's LLM. Finally, we have built an Electronic Shopping Assistant capable of answering a wide range of product-related questions based on our extensive knowledge base.

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: Methods · Consensus signal: Methods
Teacher disagreement score0.982
Threshold uncertainty score0.536

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
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 head0.036
GPT teacher head0.302
Teacher spread0.266 · 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

Citations9
Published2024
Admission routes2
Has abstractyes

Explore more

Same topicAI in Service InteractionsFrench-language works237,207