Trace and Edit Relation Associations in GPT
Abstract: This study introduces a novel approach for analyzing and modifying entity relationships in GPT models, diverging from ROME's entity-focused methods. We develop a relation tracing technique to understand the influence of LLM computations on relationship judgments. Using the FewRel dataset, we identify key roles of MLP modules and attention mechanisms in processing relationship information. Our method, tested against ROME on a new dataset, shows improved balance in specificity and generalization, underscoring the potential of manipulating early-layer modules for enhanced model understanding and accuracy.
- Knowledge neurons in pretrained transformers. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8493–8502, Dublin, Ireland. Association for Computational Linguistics.
- Editing factual knowledge in language models. arXiv preprint arXiv:2104.08164.
- Fewrel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. CoRR, abs/1810.10147.
- Locating and editing factual associations in GPT. In Advances in Neural Information Processing Systems.
- Language models as knowledge bases? In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2463–2473, Hong Kong, China. Association for Computational Linguistics.
- Attention is all you need. Advances in neural information processing systems, 30.
- Shanchan Wu and Yifan He. 2019. Enriching pre-trained language model with entity information for relation classification. In Proceedings of the 28th ACM international conference on information and knowledge management, pages 2361–2364.
- Joint extraction of entities and relations based on a novel decomposition strategy. arXiv preprint arXiv:1909.04273.
- Modifying memories in transformer models. arXiv preprint arXiv:2012.00363.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
