Detecting Machine-Generated Text Across Diverse Domains and Language Models
Combining linguistic features and language model embeddings can effectively distinguish machine-generated text from human-written text, even across unseen language models and domains.
AI-Generated Text Boundary Detection: Identifying the Transition from Human-Written to Machine-Generated Content
This work addresses the task of detecting the boundary between human-written and machine-generated parts in texts that combine both. The authors evaluate several approaches, including perplexity-based methods, topological data analysis, and fine-tuned language models, on the RoFT and RoFT-chatgpt datasets. They find that perplexity-based classifiers outperform fine-tuned language models in cross-domain and cross-model settings, and analyze the properties of the data that influence the performance of different detection methods.
A Class-balanced Soft-voting System for Detecting Multi-generator Machine-generated Text in SemEval-2024 Task 8
A robust and accurate system for detecting machine-generated text from multiple generators across different domains.
Empirical Analysis of Sampling Methods and Their Impact on Minimum Bayes-Risk Decoding Performance
The performance of minimum Bayes-risk (MBR) decoding varies significantly depending on the sampling method used to generate pseudo-references, and this variation is closely linked to how well the samples approximate the true distribution of references.
Developing an Adversarial Interface for Generating Challenging Trivia Questions to Improve Question-Answering AI
A novel interface is developed to facilitate the collection of adversarial human-written trivia questions that challenge question-answering AI models, with the goal of improving their natural language understanding and reasoning capabilities.
