Origin Tracing and Detecting of LLMs
Linyang Li, Pengyu Wang, Ke Ren, Tianxiang Sun, Xipeng Qiu

TL;DR
This paper introduces a novel, generalizable method for tracing the origin of texts generated by large language models, effective under various settings and requiring limited data, with extensive experiments and open resources.
Contribution
The paper presents an innovative contrastive feature-based algorithm for LLM origin tracing that works in both white-box and black-box scenarios, requiring minimal data and supporting new model detection.
Findings
The method effectively traces LLM origins in diverse settings.
Limited data suffices for accurate origin detection.
The approach reveals insights into AI-generated text similarities and detection challenges.
Abstract
The extraordinary performance of large language models (LLMs) heightens the importance of detecting whether the context is generated by an AI system. More importantly, while more and more companies and institutions release their LLMs, the origin can be hard to trace. Since LLMs are heading towards the time of AGI, similar to the origin tracing in anthropology, it is of great importance to trace the origin of LLMs. In this paper, we first raise the concern of the origin tracing of LLMs and propose an effective method to trace and detect AI-generated contexts. We introduce a novel algorithm that leverages the contrastive features between LLMs and extracts model-wise features to trace the text origins. Our proposed method works under both white-box and black-box settings therefore can be widely generalized to detect various LLMs.(e.g. can be generalized to detect GPT-3 models without the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Language and cultural evolution
Methods{Dispute@FaQ-s}How to file a dispute with Expedia? · Attention Is All You Need · Linear Layer · Adam · Layer Normalization · Attention Dropout · Dense Connections · Refunds@Expedia|||How do I get a full refund from Expedia? · Dropout · Weight Decay
