# OCC-RAG：为忠实问答优化的最优认知核心

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-30 08:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmpy48u2v01koslax6t6is09n
- 原文链接：https://arxiv.org/abs/2606.00683

## AI 摘要

OCC-RAG 是 Optimal Cognitive Core (OCC) 家族中专为忠实问答优化的 SLM。研究团队通过大规模合成多上下文、多跳 QA 数据（超300万样本）训练出 0.6B 和 1.7B 两个版本。模型生成结构化推理轨迹并引用原文证据。在 HotpotQA、MuSiQue、TAT-QA（多跳推理）、ConFiQA（忠实性）和 MuSiQue-Un（拒答）基准上，性能匹配或超越 2-6 倍规模的通用模型。

## 正文

Recent progress in the development of language models has been defined by scale, with each generation absorbing more of the world's knowledge into its weights. However, many practical applications benefit more from robust reasoning than from extensive parametric knowledge. In this setting, task-specialized small language models (SLMs) offer a principled design choice. We introduce Optimal Cognitive Core (OCC), a family of SLMs built around this premise. As a variant of OCC, we present OCC-RAG, optimized for faithful question answering (QA) grounded in the provided context. This task directly aligns with the OCC design approach, requiring multi-hop reasoning over supplied passages while ignoring memorized knowledge. To train OCC-RAG, we implement a novel pipeline for synthesizing multi-context, multi-hop QA data at scale, producing a corpus of over three million examples targeting multi-hop reasoning, strict context faithfulness, and calibrated abstention. We release OCC-RAG-0.6B and OCC-RAG-1.7B, both mid-trained on this corpus. The models produce structured reasoning traces with source citations grounded in literal quotes from the context. Through OCC-RAG, we demonstrate that compact, task-specialized SLMs can match or exceed general-purpose models 2 -- 6x their size across multi-hop reasoning (HotpotQA, MuSiQue, TAT-QA), faithfulness (ConFiQA), and refusal (MuSiQue-Un) benchmarks.