MétaCan
Menu
Back to cohort

A Hybrid Lightweight LLM Chatbot for Sustainable Cryptocurrency Investment Decisions: Optimizing Small Models for Domain-Specific Performance

2025· article· en· W4413640086 on OpenAlexafffund
Ali Shiri, Mikaeil Mayeli Feridani, Samira Keivanpour

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldBusiness, Management and Accounting
TopicFinTech, Crowdfunding, Digital Finance
Canadian institutionsPolytechnique Montréal
FundersMitacs
KeywordsChatbotCryptocurrencyComputer scienceDomain (mathematical analysis)Investment (military)Computer securityWorld Wide Web

Abstract

fetched live from OpenAlex

This paper presents a hybrid chatbot for sustainable cryptocurrency investment, powered by small-scale Large Language Models (LLMs). We evaluate the performance of various lightweight LLMs (under 10B parameters) on blockchain and sustainability-related tasks, demonstrating that carefully orchestrated smaller models can effectively match or exceed the performance of larger models in domain-specific applications. Our multi-agent Retrieval-Augmented Generation (RAG) pipeline, incorporating real-time sustainability metrics from the Crypto Carbon Ratings Institute, achieved 87.09% accuracy in providing investment guidance, improving upon the 72.58% baseline of individual models. The results show that refined instruction engineering and specialized pipeline architecture can significantly enhance model performance without requiring larger, more energy-intensive models. This work contributes to both the practical implementation of sustainable cryptocurrency investment tools and the broader discussion of environmental considerations in AI system design and deployment.

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.

How this classification was reachedexpand

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.633
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0010.003
Open science0.0010.000
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 head0.033
GPT teacher head0.234
Teacher spread0.201 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designTheoretical or conceptual
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes2
Has abstractyes

Explore more

Same topicFinTech, Crowdfunding, Digital FinanceFrench-language works237,207