Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2506.14146 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915348226244608 |
|---|---|
| author | Tang, Kaiwen Wu, Aitong Lu, Yao Sun, Guangda |
| author_facet | Tang, Kaiwen Wu, Aitong Lu, Yao Sun, Guangda |
| contents | Vertical-domain large language models (LLMs) play a crucial role in specialized scenarios such as finance, healthcare, and law; however, their training often relies on large-scale annotated data and substantial computational resources, impeding rapid development and continuous iteration. To address these challenges, we introduce the Collaborative Editable Model (CoEM), which constructs a candidate knowledge pool from user-contributed domain snippets, leverages interactive user-model dialogues combined with user ratings and attribution analysis to pinpoint high-value knowledge fragments, and injects these fragments via in-context prompts for lightweight domain adaptation. With high-value knowledge, the LLM can generate more accurate and domain-specific content. In a financial information scenario, we collect 15k feedback from about 120 users and validate CoEM with user ratings to assess the quality of generated insights, demonstrating significant improvements in domain-specific generation while avoiding the time and compute overhead of traditional fine-tuning workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_14146 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Collaborative Editable Model Tang, Kaiwen Wu, Aitong Lu, Yao Sun, Guangda Artificial Intelligence Vertical-domain large language models (LLMs) play a crucial role in specialized scenarios such as finance, healthcare, and law; however, their training often relies on large-scale annotated data and substantial computational resources, impeding rapid development and continuous iteration. To address these challenges, we introduce the Collaborative Editable Model (CoEM), which constructs a candidate knowledge pool from user-contributed domain snippets, leverages interactive user-model dialogues combined with user ratings and attribution analysis to pinpoint high-value knowledge fragments, and injects these fragments via in-context prompts for lightweight domain adaptation. With high-value knowledge, the LLM can generate more accurate and domain-specific content. In a financial information scenario, we collect 15k feedback from about 120 users and validate CoEM with user ratings to assess the quality of generated insights, demonstrating significant improvements in domain-specific generation while avoiding the time and compute overhead of traditional fine-tuning workflows. |
| title | Collaborative Editable Model |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.14146 |