English(EN) Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain

开源LLM在ESG报告任务中的表现评估 · 跟踪到1个来源

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

一篇新论文评估了七个开源大语言模型（LLMs）在环境、社会和治理（ESG）领域内进行检索增强生成（RAG）任务的性能。该研究使用了来自欧盟上市公司（EU-listed companies）的498份真实ESG报告和100对合成问答对来评估GLM 4.7 Flash、Nemotron-3-nano:4b和Qwen3:4b-instruct等模型。虽然模型的检索性能普遍较强，但在忠实度和事实准确性等生成指标上存在显著差异，表明需要进行领域特定的微调。 AI

影响为选择和微调用于特定ESG报告任务的开源LLM提供了数据驱动的指导。

排序理由该集群包含一篇评估开源LLM在特定领域任务上表现的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇评估开源LLM在特定领域任务上表现的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Motaz Saad, Anna Borrelli, Ivan Gentile, Kianna Kazemi, Francesco Piccialli, Antonella Longo · 2026-09-15 04:00

ESG领域中用于检索增强生成的开源大语言模型的实证评估

arXiv:2609.15242v1 Announce Type: new Abstract: Environmental, Social, and Governance (ESG) reporting is critical for corporate accountability, with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) offering strong potential to automate KPI extraction. However…

本文如何被排名

报道来源 [1]

ESG领域中用于检索增强生成的开源大语言模型的实证评估

相关实体

相关话题