← Search

Kangxi Wu

2 accepted papers

2024

Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration

EMNLP 2024main

The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) methods are considered effective solutions to address these challenges.Most recent…

2023

LLMDet: A Third Party Large Language Models Generated Text Detection Tool

EMNLP 2023long findings

Generated texts from large language models (LLMs) are remarkably close to high-quality human-authored text, raising concerns about their potential misuse in spreading false information and academic misconduct. Consequently, there is an urgent need for a highly practical detection tool capable of acc…

Cited by 0SourcecodeScholar