Using LLM-Generated Draft Replies to Support Human Experts in Responding to Stakeholder Inquiries in Maritime Industry: A Real-World Case Study of Industrial AI

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bach, Tita Alissa, Babic, Aleksandar, Park, Narae, Sporsem, Tor, Ulfsnes, Rasmus, Smith-Meyer, Henrik, Skeie, Torkel
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914387087851520
author Bach, Tita Alissa
Babic, Aleksandar
Park, Narae
Sporsem, Tor
Ulfsnes, Rasmus
Smith-Meyer, Henrik
Skeie, Torkel
author_facet Bach, Tita Alissa
Babic, Aleksandar
Park, Narae
Sporsem, Tor
Ulfsnes, Rasmus
Smith-Meyer, Henrik
Skeie, Torkel
contents The maritime industry requires effective communication among diverse stakeholders to address complex, safety-critical challenges. Industrial AI, including Large Language Models (LLMs), has the potential to augment human experts' workflows in this specialized domain. Our case study investigated the utility of LLMs in drafting replies to stakeholder inquiries and supporting case handlers. We conducted a preliminary study (observations and interviews), a survey, and a text similarity analysis (LLM-as-a-judge and Semantic Embedding Similarity). We discover that while LLM drafts can streamline workflows, they often require significant modifications to meet the specific demands of maritime communications. Though LLMs are not yet mature enough for safety-critical applications without human oversight, they can serve as valuable augmentative tools. Final decision-making thus must remain with human experts. However, by leveraging the strengths of both humans and LLMs, fostering human-AI collaboration, industries can increase efficiency while maintaining high standards of quality and precision tailored to each case.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12732
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using LLM-Generated Draft Replies to Support Human Experts in Responding to Stakeholder Inquiries in Maritime Industry: A Real-World Case Study of Industrial AI
Bach, Tita Alissa
Babic, Aleksandar
Park, Narae
Sporsem, Tor
Ulfsnes, Rasmus
Smith-Meyer, Henrik
Skeie, Torkel
Human-Computer Interaction
The maritime industry requires effective communication among diverse stakeholders to address complex, safety-critical challenges. Industrial AI, including Large Language Models (LLMs), has the potential to augment human experts' workflows in this specialized domain. Our case study investigated the utility of LLMs in drafting replies to stakeholder inquiries and supporting case handlers. We conducted a preliminary study (observations and interviews), a survey, and a text similarity analysis (LLM-as-a-judge and Semantic Embedding Similarity). We discover that while LLM drafts can streamline workflows, they often require significant modifications to meet the specific demands of maritime communications. Though LLMs are not yet mature enough for safety-critical applications without human oversight, they can serve as valuable augmentative tools. Final decision-making thus must remain with human experts. However, by leveraging the strengths of both humans and LLMs, fostering human-AI collaboration, industries can increase efficiency while maintaining high standards of quality and precision tailored to each case.
title Using LLM-Generated Draft Replies to Support Human Experts in Responding to Stakeholder Inquiries in Maritime Industry: A Real-World Case Study of Industrial AI
topic Human-Computer Interaction
url https://arxiv.org/abs/2412.12732