Knowledge Rumination for Pre-trained Language Models
This addresses the issue for NLP researchers and practitioners by improving PLMs' ability to leverage internal knowledge without external retrieval, though it is incremental as it builds on existing prompt-based methods.
The paper tackles the problem that pre-trained language models (PLMs) underutilize their encoded knowledge for knowledge-intensive tasks, proposing Knowledge Rumination to review and inject latent knowledge using prompts like 'As far as I know', resulting in enhanced performance on six commonsense reasoning tasks and GLUE benchmarks.
Previous studies have revealed that vanilla pre-trained language models (PLMs) lack the capacity to handle knowledge-intensive NLP tasks alone; thus, several works have attempted to integrate external knowledge into PLMs. However, despite the promising outcome, we empirically observe that PLMs may have already encoded rich knowledge in their pre-trained parameters but fail to fully utilize them when applying them to knowledge-intensive tasks. In this paper, we propose a new paradigm dubbed Knowledge Rumination to help the pre-trained language model utilize that related latent knowledge without retrieving it from the external corpus. By simply adding a prompt like "As far as I know" to the PLMs, we try to review related latent knowledge and inject them back into the model for knowledge consolidation. We apply the proposed knowledge rumination to various language models, including RoBERTa, DeBERTa, and GPT-3. Experimental results on six commonsense reasoning tasks and GLUE benchmarks demonstrate the effectiveness of our proposed approach, which proves that the knowledge stored in PLMs can be better exploited to enhance performance. Code is available in https://github.com/zjunlp/knowledge-rumination.