Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2311.08723 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914669485096960 |
|---|---|
| author | Chen, Yutian Kang, Hao Zhai, Vivian Li, Liangze Singh, Rita Raj, Bhiksha |
| author_facet | Chen, Yutian Kang, Hao Zhai, Vivian Li, Liangze Singh, Rita Raj, Bhiksha |
| contents | This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a next-token prediction task and directly fine-tune the base LM to perform it. We utilize the Text-to-Text Transfer Transformer (T5) model as the backbone for our experiments. We compared our approach to the more direct approach of utilizing hidden states for classification. Evaluation shows the exceptional performance of our method in the text classification task, highlighting its simplicity and efficiency. Furthermore, interpretability studies on the features extracted by our model reveal its ability to differentiate distinctive writing styles among various LLMs even in the absence of an explicit classifier. We also collected a dataset named OpenLLMText, containing approximately 340k text samples from human and LLMs, including GPT3.5, PaLM, LLaMA, and GPT2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_08723 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Token Prediction as Implicit Classification to Identify LLM-Generated Text Chen, Yutian Kang, Hao Zhai, Vivian Li, Liangze Singh, Rita Raj, Bhiksha Computation and Language This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a next-token prediction task and directly fine-tune the base LM to perform it. We utilize the Text-to-Text Transfer Transformer (T5) model as the backbone for our experiments. We compared our approach to the more direct approach of utilizing hidden states for classification. Evaluation shows the exceptional performance of our method in the text classification task, highlighting its simplicity and efficiency. Furthermore, interpretability studies on the features extracted by our model reveal its ability to differentiate distinctive writing styles among various LLMs even in the absence of an explicit classifier. We also collected a dataset named OpenLLMText, containing approximately 340k text samples from human and LLMs, including GPT3.5, PaLM, LLaMA, and GPT2. |
| title | Token Prediction as Implicit Classification to Identify LLM-Generated Text |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2311.08723 |