Conference proceeding
Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models
16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021), pp.1811-1822
01/01/2021
Abstract
Given the potential misuse of recent advances in synthetic text generation by language models (LMs), it is important to have the capacity to attribute authorship of synthetic text. While stylometric organic (i.e., human written) authorship attribution has been quite successful, it is unclear whether similar approaches can be used to attribute a synthetic text to its source LM. We address this question with the key insight that synthetic texts carry subtle distinguishing marks inherited from their source LM and that these marks can be leveraged by machine learning (ML) algorithms for attribution. We propose and test several ML-based attribution methods. Our best attributor built using a fine-tuned version of XLNet (XLNet-FT) consistently achieves excellent accuracy scores (91% to near perfect 98%) in terms of attributing the parent pre-trained LM behind a synthetic text. Our experiments show promising results across a range of experiments where the synthetic text may be generated using pre-trained LMs, fine-tuned LMs, or by varying text generation parameters.
Details
- Title: Subtitle
- Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models
- Creators
- Shaoor Munir - Lahore Univ Management Sci, Lahore, PakistanBrishna Batool - Lahore Univ Management Sci, Lahore, PakistanZubair Shafiq - Univ Calif Davis, Davis, CA 95616 USAPadmini Srinivasan - Univ Iowa, Iowa City, IA USAFareed Zaffar - Lahore Univ Management Sci, Lahore, PakistanAssociation for Computational Linguistics
- Resource Type
- Conference proceeding
- Publication Details
- 16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021), pp.1811-1822
- Publisher
- Assoc Computational Linguistics-Acl
- Number of pages
- 12
- Language
- English
- Date published
- 01/01/2021
- Academic Unit
- Business Analytics; Nursing; Computer Science
- Record Identifier
- 9984339312002771
Metrics
2 Record Views