Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI assistants misrepresent news content 45% of the time

bbc.co.uk

Post reply on HN
Print view View original

181–190 of 306 posts

Re: AI assistants misrepresent news content 45% of the time

#181

Post by bunderbunder »

gamerDude wrote: post #117
bunderbunder wrote: post #108

Earlier quoted context omitted.

The biggest problem with that citation isn't that the article has since been deleted. The biggest problem is that that particular Wikipedia article was never a good source in the first place. That seems to be the real challenge with AI for this use case. It has no real critical thinking skills, so it's not really competent to choose reliable sources. So instead we're lowering the bar to just asking that the sources a…

I think this is a real challenge for everyone. In many ways potentially we need a restart of a wikipedia like site to document all the valid and good sources. This would also hopefully include things like source bias and whether it's a primary/secondary/tertiary source.

Outsourcing due diligence to a tool (or a single unified source) is the problem, not the solution.

For example, having a single central arbiter of source bias is inescapably the most biased thing you could possibly do. Bias has to be defined within an intellectual paradigm. So you'd have to choose a paradigm to use for that bias evaluation, and de facto declare it to be the one true paradigm for this purpose. But intellectual paradigms are inherently subjective, so doing that is pretty much the most intellectually biased thing you can possibly do.

Re: AI assistants misrepresent news content 45% of the time

#182

Post by scarmig »

scellus wrote: post #150
scarmig wrote: post #38

If you dig into the actual report (I know, I know, how passe), you see how they get the numbers. Most of the errors are "sourcing issues": the AI assistant doesn't cite a claim, or it (shocking) cites Wikipedia instead of the BBC. Other issues: the report doesn't even say which particular models it's querying [ETA: discovered they do list this in an appendix], aside from saying it's the consumer tier. And it leaves o…

Are citation issues related to the fact that https://www.bbc.co.uk/robots.txt denies a lot of AI, both user agents and crawlers?

The report says that different media organizations dropped their robots.txt for the duration of the research to give LLMs access.

I would expect this isn't the on-off switch they conceptualized, but I don't know enough about how different LLM providers handle news search and retrieval to say for sure.

Re: AI assistants misrepresent news content 45% of the time

#183

Post by mckngbrd »

visarga wrote: post #20

I recently tried to get Gemini to collect fresh news and show them to me, and instead of using search it hallucinated everything wholesale, titles, abstracts and links. Not just once, multiple times. I am kind of afraid of using Gemini now for anything related to web search. Here is a sample: > [1] Google DeepMind and Harvard researchers propose a new method for testing the ‘theory of mind’ of LLMs - Researchers have…

What version of Gemini were you using? i.e. were you calling it locally via the API or thru their Gemini or AI Studio web apps?

Not every LLM app has access to web / news search capabilities turned on by default. This makes a huge difference in what kind of results you should expect. Of course, the AI should be aware that it doesn't have access to web / news search, and it should tell you as much rather than hallucinating fake links. If access to web search was turned on, and it still didn't properly search the web for you, that's a problem as well.

Re: AI assistants misrepresent news content 45% of the time

#184

Post by LeifCarrotson »

jacobolus wrote: post #87
hnuser123456 wrote: post #57

Earlier quoted context omitted.

Do we have any good research on how much less often larger, newer models will just make stuff up like this? As it is, it's pretty clear LLMs are categorically not a good idea for directly querying for information in any non-fiction-writing context. If you're using an LLM to research something that needs to be accurate, the LLM needs to be doing a tool call to a web search and only asked to summarize relevant facts fr…

A further problem is that Wikipedia is chock full of nonsense, with a large proportion of articles that were never fact checked by an expert, and many that were written to promote various biased points of view, inadvertently uncritically repeat claims from slanted sources, or mischaracterize claims made in good sources. Many if not most articles have poor choice of emphasis of subtopics, omit important basic topics,…

A future problem will be that the BBC and the rest of the Internet will soon be chock-full of nonsense, with a large proportion of articles that were never fact checked by a human, much less an AI.

Re: AI assistants misrepresent news content 45% of the time

#185

Post by bongodongobob »

Yizahi wrote: post #79
visarga wrote: post #20

I recently tried to get Gemini to collect fresh news and show them to me, and instead of using search it hallucinated everything wholesale, titles, abstracts and links. Not just once, multiple times. I am kind of afraid of using Gemini now for anything related to web search. Here is a sample: > [1] Google DeepMind and Harvard researchers propose a new method for testing the ‘theory of mind’ of LLMs - Researchers have…

But LLM can't collect anything. It can generate the most likely characters in a row. What exactly did you expect from it?

LLMs have been able to search the web for a couple years now.

Re: AI assistants misrepresent news content 45% of the time

#186

Post by latexr »

BeetleB wrote: post #74

Actual news articles misrepresent reality more often than 45%. Some very recent discussions on HN: https://news.ycombinator.com/item?id=45617088 https://news.ycombinator.com/item?id=45585323

How exactly did you arrive at that conclusion? What in your examples is proof of that “more than 45%” statement? I’m not seeing it.

But even if we concede that to be true, it doesn’t change the fact that LLMs are misrepresenting the text they’ve been given half the time. Which means the information is degraded further. Which is worse.

I guess I don’t exactly understand the point you’re trying to make.

Re: AI assistants misrepresent news content 45% of the time

#187

Post by bongodongobob »

everdrive wrote: post #22

It's important to bear this in mind whenever you find out that someone uses an LLM to summarize a meeting, email, or other communication you've held. That person is not really getting the message you were conveying.

We have been using MS Copilot in our meetings for months and it does a very good job summarizing who said what and who has what deliverables. It's extremely useful and I've found it to be very accurate.

Re: AI assistants misrepresent news content 45% of the time

#188

Post by ekidd »

hnuser123456 wrote: post #57
afavour wrote: post #42

Earlier quoted context omitted.

> or it (shocking) cites Wikipedia instead of the BBC. No... the problem is that it cites Wikipedia articles that don't exist . > ChatGPT linked to a non-existent Wikipedia article on the “European Union Enlargement Goals for 2040”. In fact, there is no official EU policy under that name. The response hallucinates a URL but also, indirectly, an EU goal and policy.

Do we have any good research on how much less often larger, newer models will just make stuff up like this? As it is, it's pretty clear LLMs are categorically not a good idea for directly querying for information in any non-fiction-writing context. If you're using an LLM to research something that needs to be accurate, the LLM needs to be doing a tool call to a web search and only asked to summarize relevant facts fr…

"Truth" is often a very expensive commodity to obtain. There are plenty of awful sources and mistaken claims on the shelf of any town library. Lots of peer reviewed papers are crap, including a few in Nature. Newspapers are constantly wrong and misleading. Digging through even "reliable" sources can require significant expertise. (This is, in fact, a significant part of PhD training, according to the PhDs and professors I know: Learning to use the literature well.)

One way to successfully use LLMs is to do the initial research legwork. Run the 40 Google searches and follow links. Evaluate sources according to some criteria. Summarize. And then give the human a list of links to follow.

You quickly learn to see patterns. Sonnet will happily give a genuinely useful rule of thumb, phrasing it like it's widely accepted. But the source will turn out to be "one guy on a forum."

There are other tricks that work well. Have the LLM write an initial overview with sources. Tell it strictly limit itself to information in the sources, etc. Then hand the report off to a fresh LLM and tell it to carefully check each citation in the report, removing unsourced information. Then have the human review the output, following links.

None of this will get you guaranteed truth. But if you know what you're doing, it can often give you a better starting point than Wikipedia or anything on the first two pages of Google Search results. Accurate information is genuinely hard to get, and it always has been.

Post reply on HN