Editing Knowledge Representation of Language Model via Rephrased Prefix Prompts
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914792786100224 |
|---|---|
| author | Cai, Yuchen Cao, Ding Guo, Rongxi Wen, Yaqin Liu, Guiquan Chen, Enhong |
| author_facet | Cai, Yuchen Cao, Ding Guo, Rongxi Wen, Yaqin Liu, Guiquan Chen, Enhong |
| contents | Neural language models (LMs) have been extensively trained on vast corpora to store factual knowledge about various aspects of the world described in texts. Current technologies typically employ knowledge editing methods or specific prompts to modify LM outputs. However, existing knowledge editing methods are costly and inefficient, struggling to produce appropriate text. Additionally, prompt engineering is opaque and requires significant effort to find suitable prompts. To address these issues, we introduce a new method called PSPEM (Prefix Soft Prompt Editing Method), that can be used for a lifetime with just one training. It resolves the inefficiencies and generalizability issues in knowledge editing methods and overcomes the opacity of prompt engineering by automatically seeking optimal soft prompts. Specifically, PSPEM utilizes a prompt encoder and an encoding converter to refine key information in prompts and uses prompt alignment techniques to guide model generation, ensuring text consistency and adherence to the intended structure and content, thereby maintaining an optimal balance between efficiency and accuracy. We have validated the effectiveness of PSPEM through knowledge editing and attribute inserting. On the COUNTERFACT dataset, PSPEM achieved nearly 100\% editing accuracy and demonstrated the highest level of fluency. We further analyzed the similarities between PSPEM and original prompts and their impact on the model's internals. The results indicate that PSPEM can serve as an alternative to original prompts, supporting the model in effective editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14381 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Editing Knowledge Representation of Language Model via Rephrased Prefix Prompts Cai, Yuchen Cao, Ding Guo, Rongxi Wen, Yaqin Liu, Guiquan Chen, Enhong Computation and Language Artificial Intelligence Neural language models (LMs) have been extensively trained on vast corpora to store factual knowledge about various aspects of the world described in texts. Current technologies typically employ knowledge editing methods or specific prompts to modify LM outputs. However, existing knowledge editing methods are costly and inefficient, struggling to produce appropriate text. Additionally, prompt engineering is opaque and requires significant effort to find suitable prompts. To address these issues, we introduce a new method called PSPEM (Prefix Soft Prompt Editing Method), that can be used for a lifetime with just one training. It resolves the inefficiencies and generalizability issues in knowledge editing methods and overcomes the opacity of prompt engineering by automatically seeking optimal soft prompts. Specifically, PSPEM utilizes a prompt encoder and an encoding converter to refine key information in prompts and uses prompt alignment techniques to guide model generation, ensuring text consistency and adherence to the intended structure and content, thereby maintaining an optimal balance between efficiency and accuracy. We have validated the effectiveness of PSPEM through knowledge editing and attribute inserting. On the COUNTERFACT dataset, PSPEM achieved nearly 100\% editing accuracy and demonstrated the highest level of fluency. We further analyzed the similarities between PSPEM and original prompts and their impact on the model's internals. The results indicate that PSPEM can serve as an alternative to original prompts, supporting the model in effective editing. |
| title | Editing Knowledge Representation of Language Model via Rephrased Prefix Prompts |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.14381 |