Back to Home
arXiv AI··Papers & Tech

KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks

中文摘要

KDASO提出知识-数据双驱动方法,通过自动优化技能解决责任认定任务中大语言模型技能库陈旧的问题。

English Summary

KDASO introduces a knowledge-data dual-driven approach to automatically optimize skills for liability adjudication, addressing stale skill libraries in LLM-based legal reasoning.

Original Excerpt

arXiv:2611.06972v1 Announce Type: new Abstract: Liability adjudication tasks (e.g., legal charge determination) require analyzing event descriptions against domain-specific skills to determine whether a party should bear liability. While Large Language Models (LLMs) have shown promise in this area by leveraging executable skills for interpretable reasoning, existing approaches face three critical limitations: skill libraries become stale as real-world scenarios dynamically evolve, skill descriptions often suffer from a semantic execution gap where LLMs deviate from intended expert logic, and growing skill collections exceed context budgets causing critical skill omission. To address these challenges, we propose Knowledge-Data Dual-Driven Automated Skill Optimization (KDASO), which continuously evolves a skill library through neighborhood-conditioned induction from recent adjudication data, execution-aligned refinement based on LLM trajectory analysis, and context-budgeted routing for scalable skill selection. Experiments across ride-hailing adjudication, legal liability determination, and logical reasoning judgment demonstrate that KDASO significantly outperforms current general-pu…