Scholarlink

<p>Thousands of ocean science papers are published each year, yet much of this knowledge remains inaccessible to the non-expert decision-makers advancing ocean sustainability. General-purpose large language models (LLMs) offer a pathway to synthesis but often fall short on reliability, transparency, and scientific grounding. We present IPOSGPT, a domain-specific LLM grounded on a curated corpus of peer-reviewed literature, intergovernmental reports, and environmental policy documents. Across 25 policy-relevant queries, IPOSGPT outperformed leading generalist models (gpt-4o, gemini-2.0-flash, sonnet-4, sonar-pro) on citation credibility and traceability, producing zero fabricated references compared with over 95 percent invalid citations on average for baselines. On answer quality, IPOSGPT was competitive, frequently ranking second while maintaining strict faithfulness to evidence. In a Seychelles case study, the system accelerated assessment of circular economy options to reduce marine pollution. These results show that domain-specific LLMs can deliver trusted synthesis for high-stakes sustainability policy, addressing hallucination, source integrity, and accountability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Trustworthy AI for the ocean: bridging the science-policy divide

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月26日

查看全文
  • Arjun Pankajakshan,
  • Joi Danielson,
  • Zifu Wang,
  • Prabhjot Singh,
  • Manish Mehra,
  • Bhushan Pawar,
  • Madhu Reddiboina,
  • Eline De Buyser,
  • Ramez Tawil,
  • Shefali Mehta,
  • Kelsey Archer Barnhill,
  • Maxime de Lisle,
  • Françoise Gaill,
  • Guillermo Ortuno Crespo,
  • Henrik Oksfeldt Enevoldsen,
  • Xavier Fresquet,
  • Eloi Astier,
  • Allan González Estrada,
  • Tanya Brodie Rudolph

摘要

Thousands of ocean science papers are published each year, yet much of this knowledge remains inaccessible to the non-expert decision-makers advancing ocean sustainability. General-purpose large language models (LLMs) offer a pathway to synthesis but often fall short on reliability, transparency, and scientific grounding. We present IPOSGPT, a domain-specific LLM grounded on a curated corpus of peer-reviewed literature, intergovernmental reports, and environmental policy documents. Across 25 policy-relevant queries, IPOSGPT outperformed leading generalist models (gpt-4o, gemini-2.0-flash, sonnet-4, sonar-pro) on citation credibility and traceability, producing zero fabricated references compared with over 95 percent invalid citations on average for baselines. On answer quality, IPOSGPT was competitive, frequently ranking second while maintaining strict faithfulness to evidence. In a Seychelles case study, the system accelerated assessment of circular economy options to reduce marine pollution. These results show that domain-specific LLMs can deliver trusted synthesis for high-stakes sustainability policy, addressing hallucination, source integrity, and accountability.