跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-17AI 評分32

CoRE 如何協同學習規則路由與約束式結構化知識檢索

Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval

AI 導讀

CoRE 提出一種無需預設查詢與規則配對監督的結構化知識檢索方法,協同學習為查詢選擇推理規則,以及依規則約束檢索證據。它交替使用強化學習訓練路由策略,並以對比學習訓練檢索器。在 STaRK-QA 的科學發現、生物醫學推理和電子商務知識管理數據集上,實驗顯示 CoRE 有效;分析亦顯示規則使用情況可用於自動改進和發現規則。

正文

Published on Oct 17

Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

CoRE jointly learns reasoning rules and constrained evidence retrieval through alternating reinforcement and contrastive learning without predefined query-rule supervision.

Structured knowledge retrieval acquires task-relevant evidence from structured knowledge sources for downstream tasks. Existing methods rely on unconstrained retrieval or predefined query-rule supervision, such as author-paper rules for scientific discovery and anatomy-drug rules for precision medicine. Such supervision is rarely available in practice. We propose Co-Adaptive Rule Routing and Constraining Retrieval (CoRE), which jointly learns which reasoning rule to assign to each query and how to retrieve evidence under that rule, without predefined query-rule pairs. A routing agent selects a rule, and its corresponding retriever traverses the knowledge base and ranks evidence that satisfies the rule's constraints. Because routing and retrieval are interdependent, CoRE alternates between reinforcement learning for the routing policy and contrastive learning for the rule-constrained retriever. The selected rules provide supervision for retriever training, while retrieval performance rewards the routing policy. This closed-loop process enables both components to co-adapt without explicit query-rule supervision. Experiments on STaRK-QA datasets across scientific discovery, biomedical reasoning, and e-commerce knowledge management demonstrate CoRE's effectiveness. Ablations show the benefit of co-adapting the router and retriever. Generation-based routing transfers across datasets and benefits from multi-domain pretraining followed by target-specific fine-tuning. Analysis of rule usage across queries also informs automatic rule refinement and discovery.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.14465

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.14465 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.14465 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.14465 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co