תקציר
Despite the many advances of Large Language Models (LLMs) and their unprecedented rapid evolution, their impact and integration into every facet of our daily lives is limited due to various reasons. One critical factor hindering their widespread adoption is the occurrence of hallucinations, where LLMs invent answers that sound realistic, yet drift away from factual truth. In this paper, we present a novel method for detecting hallucinations in large language models, which tackles a critical issue in the adoption of these models in various real-world scenarios. Through extensive evaluations across multiple datasets and LLMs, including Llama-2, we study the hallucination levels of various recent LLMs and demonstrate the effectiveness of our method to automatically detect them. Notably, we observe up to 87% hallucinations for Llama-2 in a specific experiment, where our method achieves a Balanced Accuracy of 81%, all without relying on external knowledge.
שפה מקורית | אנגלית |
---|---|
כותר פרסום המארח | Long Papers |
עורכים | Lun-Wei Ku, Andre F. T. Martins, Vivek Srikumar |
מוציא לאור | Association for Computational Linguistics (ACL) |
עמודים | 9333-9347 |
מספר עמודים | 15 |
מסת"ב (אלקטרוני) | 9798891760943 |
סטטוס פרסום | פורסם - 2024 |
פורסם באופן חיצוני | כן |
אירוע | 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024 - Bangkok, תאילנד משך הזמן: 11 אוג׳ 2024 → 16 אוג׳ 2024 |
סדרות פרסומים
שם | Proceedings of the Annual Meeting of the Association for Computational Linguistics |
---|---|
כרך | 1 |
ISSN (מודפס) | 0736-587X |
כנס
כנס | 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024 |
---|---|
מדינה/אזור | תאילנד |
עיר | Bangkok |
תקופה | 11/08/24 → 16/08/24 |
הערה ביבליוגרפית
Publisher Copyright:© 2024 Association for Computational Linguistics.