Bag of Lies: Robustness in Continuous Pre-training BERT
원문 초록
This study aims to acquire more insights into the continuous pre-training phase of BERT regarding entity knowledge, using the COVID-19 pandemic as a case study. Since the pandemic emerged after the last update of BERT's pre-training data, the model has little to no entity knowledge about COVID-19. Using continuous pre-training, we control what entity knowledge is available to the model. We compare the baseline BERT model with the further pre-trained variants on the fact-checking benchmark Check-COVID. To test the robustness of continuous pre-training, we experiment with several adversarial methods to manipulate the input data, such as training on misinformation and shuffling the word order until the input becomes nonsensical. Surprisingly, our findings reveal that these methods do not degrade, and sometimes even improve, the model's downstream performance. This suggests that continuous pre-training of BERT is robust against misinformation. Furthermore, we are releasing a new dataset, consisting of original texts from academic publications in the LitCovid repository and their AI-generated false counterparts.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking
SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing
Entity-aware Cross-lingual Claim Detection for Automated Fact-checking
When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits
SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking
Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking
토론
이 논문과 연결된 포럼 글이 아직 없습니다.