Unveiling the Black Box: The Significance of XAI in Making LLMs Transparent

Unveiling the Black Box: The Significance of XAI in Making LLMs Transparent | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 18 February 2025 V1 Latest version Share on Unveiling the Black Box: The Significance of XAI in Making LLMs Transparent Authors : Murillo Edson de Carvalho Souza 0000-0002-3827-1952 [email protected] and Li Weigang Authors Info & Affiliations https://doi.org/10.22541/au.173991264.46233479/v1 1365 views 709 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract As Large Language Models (LLMs) continue to evolve, their black-box nature poses significant challenges in terms of interpretability, trust, and accountability. Explainable Artificial Intelligence (XAI) emerges as a crucial approach to making these models more transparent by providing insights into their decision-making processes. This paper explores the significance of XAI techniques in enhancing the interpretability of LLMs, examining key methodologies, such as attention visualization, feature attribution, and surrogate modeling. Additionally, we discuss the implications of transparent AI systems in critical domains, addressing ethical concerns, bias mitigation, and regulatory compliance. By unveiling the black box, we aim to bridge the gap between high-performance AI and human-understandable explanations, fostering more reliable and accountable AI systems. Supplementary Material File (unveiling_the_black_box__the_significance_of_xai_in_making_llms_transparent (5).pdf) Download 154.94 KB Information & Authors Information Version history V1 Version 1 18 February 2025 Copyright This work is licensed under a Creative Commons Attribution 4.0 International License Keywords bias mitigation explainable ai interpretability large language models model explainability transparency trustworthy ai Authors Affiliations Murillo Edson de Carvalho Souza 0000-0002-3827-1952 [email protected] Departamento de Ciência da Computac ¸ão, Universidade de Brasília View all articles by this author Li Weigang Departamento de Ciência da Computac ¸ão, Universidade de Brasília View all articles by this author Metrics & Citations Metrics Article Usage 1365 views 709 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Murillo Edson de Carvalho Souza, Li Weigang. Unveiling the Black Box: The Significance of XAI in Making LLMs Transparent. Authorea . 18 February 2025. DOI: https://doi.org/10.22541/au.173991264.46233479/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); Cited by Francisco Herrera, Salvador García, María José del Jesus, Luciano Sánchez, Marcos López de Prado, Co-Explainers: A Position on Interactive XAI for Human–AI Collaboration as a Harm-Mitigation Infrastructure, Machine Learning and Knowledge Extraction, 8 , 3, (69), (2026). https://doi.org/10.3390/make8030069 Crossref Hadiseh Moradisani, Fattane Zarrinkalam, Zeinab Noorian, Faezeh Ensan, Exploring unanswerability in machine reading comprehension: approaches, benchmarks, and open challenges, Artificial Intelligence Review, 59 , 1, (2025). https://doi.org/10.1007/s10462-025-11421-5 Crossref Loading... View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.173991264.46233479/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a0026a2b0defc13d',t:'MTc3OTUyMjA0OQ=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();