On the legal implications of Large Language Model answers: A prompt engineering approach and a view beyond by exploiting Knowledge Graphs
With the recent surge in popularity of Large Language Models (LLMs), there is the rising risk of users blindly trusting the information in the response. Nevertheless, there are cases where the LLM recommends actions that have potential legal implications and this may put the user in danger. We provi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Web Semantics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1570826824000295 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841545561410371584 |
|---|---|
| author | George Hannah Rita T. Sousa Ioannis Dasoulas Claudia d’Amato |
| author_facet | George Hannah Rita T. Sousa Ioannis Dasoulas Claudia d’Amato |
| author_sort | George Hannah |
| collection | DOAJ |
| description | With the recent surge in popularity of Large Language Models (LLMs), there is the rising risk of users blindly trusting the information in the response. Nevertheless, there are cases where the LLM recommends actions that have potential legal implications and this may put the user in danger. We provide an empirical analysis on multiple existing LLMs showing the urgency of the problem. Hence, we propose a first short-term solution, consisting in an approach for isolating these legal issues through prompt engineering. We prove that this solution is able to stem some risks related to legal implications, nonetheless we also highlight some limitations. Hence, we argue on the need for additional knowledge-intensive resources and specifically Knowledge Graphs for fully solving these limitations. For the purpose, we draw our proposal aiming at designing and developing a solution powered by a legal Knowledge Graph (KG) that, besides capturing and alerting the user on possible legal implications coming from the LLM answers, is also able to provide actual evidence for them by supplying citations of the interested laws. We conclude with a brief discussion on the issues that may be needed to solve for building a comprehensive legal Knowledge Graph |
| format | Article |
| id | doaj-art-1601d535c00b454892c72f0dffc58d6c |
| institution | Kabale University |
| issn | 1570-8268 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Web Semantics |
| spelling | doaj-art-1601d535c00b454892c72f0dffc58d6c2025-01-12T05:24:29ZengElsevierWeb Semantics1570-82682025-01-0184100843On the legal implications of Large Language Model answers: A prompt engineering approach and a view beyond by exploiting Knowledge GraphsGeorge Hannah0Rita T. Sousa1Ioannis Dasoulas2Claudia d’Amato3Department of Computer Science, Brownlow Hill, Liverpool, L69 7ZX, United KingdomData and Web Science Group, B6 26, Mannheim, 68159, Baden-Württemberg, GermanyLeuven.AI – Flanders Make@KULeuven, Oude Markt 13, Leuven, 3000, Vlaams-Brabant, BelgiumDepartment of Computer Science, Via Orabona, 4, Bari, 70126, Italy; Corresponding author.With the recent surge in popularity of Large Language Models (LLMs), there is the rising risk of users blindly trusting the information in the response. Nevertheless, there are cases where the LLM recommends actions that have potential legal implications and this may put the user in danger. We provide an empirical analysis on multiple existing LLMs showing the urgency of the problem. Hence, we propose a first short-term solution, consisting in an approach for isolating these legal issues through prompt engineering. We prove that this solution is able to stem some risks related to legal implications, nonetheless we also highlight some limitations. Hence, we argue on the need for additional knowledge-intensive resources and specifically Knowledge Graphs for fully solving these limitations. For the purpose, we draw our proposal aiming at designing and developing a solution powered by a legal Knowledge Graph (KG) that, besides capturing and alerting the user on possible legal implications coming from the LLM answers, is also able to provide actual evidence for them by supplying citations of the interested laws. We conclude with a brief discussion on the issues that may be needed to solve for building a comprehensive legal Knowledge Graphhttp://www.sciencedirect.com/science/article/pii/S1570826824000295Knowledge GraphLarge Language ModelsPrompt engineeringLegislative texts |
| spellingShingle | George Hannah Rita T. Sousa Ioannis Dasoulas Claudia d’Amato On the legal implications of Large Language Model answers: A prompt engineering approach and a view beyond by exploiting Knowledge Graphs Web Semantics Knowledge Graph Large Language Models Prompt engineering Legislative texts |
| title | On the legal implications of Large Language Model answers: A prompt engineering approach and a view beyond by exploiting Knowledge Graphs |
| title_full | On the legal implications of Large Language Model answers: A prompt engineering approach and a view beyond by exploiting Knowledge Graphs |
| title_fullStr | On the legal implications of Large Language Model answers: A prompt engineering approach and a view beyond by exploiting Knowledge Graphs |
| title_full_unstemmed | On the legal implications of Large Language Model answers: A prompt engineering approach and a view beyond by exploiting Knowledge Graphs |
| title_short | On the legal implications of Large Language Model answers: A prompt engineering approach and a view beyond by exploiting Knowledge Graphs |
| title_sort | on the legal implications of large language model answers a prompt engineering approach and a view beyond by exploiting knowledge graphs |
| topic | Knowledge Graph Large Language Models Prompt engineering Legislative texts |
| url | http://www.sciencedirect.com/science/article/pii/S1570826824000295 |
| work_keys_str_mv | AT georgehannah onthelegalimplicationsoflargelanguagemodelanswersapromptengineeringapproachandaviewbeyondbyexploitingknowledgegraphs AT ritatsousa onthelegalimplicationsoflargelanguagemodelanswersapromptengineeringapproachandaviewbeyondbyexploitingknowledgegraphs AT ioannisdasoulas onthelegalimplicationsoflargelanguagemodelanswersapromptengineeringapproachandaviewbeyondbyexploitingknowledgegraphs AT claudiadamato onthelegalimplicationsoflargelanguagemodelanswersapromptengineeringapproachandaviewbeyondbyexploitingknowledgegraphs |