Collaborative Editable Model

TL;DR

The paper introduces CoEM, a lightweight domain adaptation method for large language models that uses user feedback and knowledge snippets to improve domain-specific content generation without extensive retraining.

Contribution

CoEM is a novel framework that constructs a knowledge pool from user contributions and uses interactive dialogues and ratings for efficient domain adaptation of LLMs.

Findings

Significant improvements in domain-specific generation quality.

Validated with 15k user feedback in finance.

Avoids heavy fine-tuning overhead.

Abstract

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.