TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Cheng, Lu, Xinyang, Ng, See-Kiong, Low, Bryan Kian Hsiang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911946783064064
author Wang, Cheng
Lu, Xinyang
Ng, See-Kiong
Low, Bryan Kian Hsiang
author_facet Wang, Cheng
Lu, Xinyang
Ng, See-Kiong
Low, Bryan Kian Hsiang
contents The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and transparency of LLM responses. Reliable source attribution is essential to adhering to stringent legal and regulatory standards, including those set forth by the General Data Protection Regulation. Despite the well-established methods in source attribution within the computer vision domain, the application of robust attribution frameworks to natural language processing remains underexplored. To bridge this gap, we propose a novel and versatile TRansformer-based Attribution framework using Contrastive Embeddings called TRACE that, in particular, exploits contrastive learning for source attribution. We perform an extensive empirical evaluation to demonstrate the performance and efficiency of TRACE in various settings and show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04981
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs
Wang, Cheng
Lu, Xinyang
Ng, See-Kiong
Low, Bryan Kian Hsiang
Computation and Language
Machine Learning
The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and transparency of LLM responses. Reliable source attribution is essential to adhering to stringent legal and regulatory standards, including those set forth by the General Data Protection Regulation. Despite the well-established methods in source attribution within the computer vision domain, the application of robust attribution frameworks to natural language processing remains underexplored. To bridge this gap, we propose a novel and versatile TRansformer-based Attribution framework using Contrastive Embeddings called TRACE that, in particular, exploits contrastive learning for source attribution. We perform an extensive empirical evaluation to demonstrate the performance and efficiency of TRACE in various settings and show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of LLMs.
title TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2407.04981