English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The wide applicability and adaptability of generative large language models(LLMs) has enabled their rapid adoption. While the pre-trained models canperform many tasks, such models are often fine-tuned to improve theirperformance on various downstream applications. However, this leads to issuesover violation of model licenses, model theft, and copyright infringement.Moreover, recent advances show that generative technology is capable ofproducing harmful content which exacerbates the problems of accountabilitywithin model supply chains. Thus, we need a method to investigate how a modelwas trained or a piece of text was generated and what their pre-trained basemodel was. In this paper we take the first step to address this open problem bytracing back the origin of a given fine-tuned LLM to its correspondingpre-trained base model. We consider different knowledge levels and attributionstrategies, and find that we can correctly trace back 8 out of the 10 finetuned models with our best method.

Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models