[HN Gopher] STORM: Get a Wikipedia-like report on your topic
       ___________________________________________________________________
        
       STORM: Get a Wikipedia-like report on your topic
        
       Author : fragmede
       Score  : 31 points
       Date   : 2024-09-16 08:12 UTC (1 days ago)
        
 (HTM) web link (storm.genie.stanford.edu)
 (TXT) w3m dump (storm.genie.stanford.edu)
        
       | chankstein38 wrote:
       | Does anyone have more info on this? They thank Azure at the top
       | so I'm assuming it's a flavor of GPT? How do they prevent
       | hallucinations? I am always cautious about asking an LLM for
       | facts because half of the time it feels like it just adds
       | whatever it wants. So I'm curious if they addressed that here or
       | if this is just poorly thought-out...
        
         | EMIRELADERO wrote:
         | Here's the paper: https://arxiv.org/abs/2402.14207
        
           | akiselev wrote:
           | And the code: https://github.com/stanford-oval/storm
        
           | morsch wrote:
           | Thanks. There's an example page (markdown) at the very end.
           | You can pretty easily spot some weaknesses in the generated
           | text, it's uncanny valley territory. The most interesting
           | thing is that the article contains numbered references, but
           | unfortunately those footnotes are missing from the example.
        
         | infecto wrote:
         | If you ask an LLM what color is the sky it might say purple but
         | if you give it a paragraph describing the atmosphere and then
         | ask the same question it will almost always answer correctly. I
         | don't think hallucinations are as big of a problem as people
         | make them out to be.
        
           | pistoriusp wrote:
           | Yet remains unsolvable.
        
             | infecto wrote:
             | Huh?
        
           | chx wrote:
           | There are no hallucinations. It's just the normal bullshit
           | people hang a more palatable name on. _There is nothing
           | else_.
           | 
           | https://hachyderm.io/@inthehands/112006855076082650
           | 
           | > You might be surprised to learn that I actually think LLMs
           | have the potential to be not only fun but genuinely useful.
           | "Show me some bullshit that would be typical in this context"
           | can be a genuinely helpful question to have answered, in code
           | and in natural language -- for brainstorming, for seeing
           | common conventions in an unfamiliar context, for having
           | something crappy to react to.
           | 
           | > Alas, that does not remotely resemble how people are
           | pitching this technology.
        
           | misnome wrote:
           | So, it only works if you already know enough about the
           | problem to not need to ask the LLM, check.
        
             | keiferski wrote:
             | No, if the _data_ you're querying contains the information
             | you need, then it is mostly fine to ask for that data in a
             | format amendable to your needs.
        
               | o11c wrote:
               | The problem with LLMs is _not_ a data problem. LLMs are
               | stupid even on data they just generated.
               | 
               | One recent catastrophic failure I found: Ask an LLM to
               | generate 10 pieces of data. Then in a second input, ask
               | it to select (say) only numbers 1, 3, and 5 from the
               | list. The LLM will probably return results _numbered_ 1,
               | 3, and 5, but chances are at least one of them will
               | actually copy the data from a different number.
        
             | infecto wrote:
             | Are you just writing negative posts without even seeing the
             | product? The system queries the internet, aggregates that
             | information and writes information based on your query.
        
       | DylanDmitri wrote:
       | Seems a promising approach. Feedback at the bottom is (?) missing
       | a submit button. Article was fine, but veered into overly verbose
       | with redundant sections. A simplification pass, even on the
       | outline, could help.
        
         | kingkongjaffa wrote:
         | It auto-saves I believe.
        
       | thebuguy wrote:
       | for the sources it used the crappy AI generated websites that pop
       | up in the first page of google
        
       | globular-toast wrote:
       | What's the point of the "elaborate on purpose" box? It makes you
       | fill it in but doesn't seem to affect the article, at least not
       | that I can tell.
        
         | mrpf1ster wrote:
         | Probably just metadata about the request for the researchers at
         | Stanford
        
       | jedberg wrote:
       | Did anyone figure out how to share the article after you generate
       | it?
        
         | philipkglass wrote:
         | I think that you have to download the PDF and upload it to your
         | own site.
         | 
         | They have a "Discover" page with previously generated articles,
         | but I think that they have some sort of manual review process
         | to enable public access and it's not updated frequently. The
         | newest articles there were from July. I tried copying the link
         | for a previously generated article of mine and opening it from
         | a private browser window but I just get sent to the main site.
        
         | ssalka wrote:
         | I'm guessing this just isn't implemented yet. It feels like a
         | very alpha-stage project, when I sign in with another account
         | and use the URL from my previous session, it tries generating
         | the article again, but seems to be hanging. Also, my 2nd
         | account is unable to view the Discover page: a 403 error in dev
         | tools says "User has not accepted consent form"
         | 
         | I would think sharing by URL _should_ work, but has some bugs
         | with it currently.
        
           | jedberg wrote:
           | Same experience. Tried sharing by URL and had the same issues
           | you did.
        
       | dvt wrote:
       | I want to build this locally, I think it would be an absolute
       | killer product. Could also consider doing an internet "deep dive"
       | where the agent would browse for maybe 1-2 hours before sorting &
       | collating the data. Add multi-modality for even more
       | intelligence-gathering.
        
       | kingkongjaffa wrote:
       | Very cool! I asked it to create an article on the topic of my
       | thesis and it was very good, but it lacked nuance and second
       | order thinking i.e. here's the thing, what are the consequences
       | of it and potential mitigations. It was able to pull existing
       | thinking on a topic but not really synthesise a novel insight.
       | 
       | Synthesis of Topic Outlines through Retrieval and Multi-
       | perspective Question Asking.
       | 
       | From the paper it seems like this is only marginally better than
       | the benchmark approach they used to compare against:
       | 
       | >Outline-driven RAG (oRAG), which is identical to RAG in outline
       | creation, but
       | 
       | >further searches additional information with section titles to
       | generate the article section by section
       | 
       | It seems like the key ingredients are:
       | 
       | - generating questions
       | 
       | - addressing the topic from multiple perspectives
       | 
       | - querying similar wikipedia articles (A high quality RAG source
       | for facts)
       | 
       | - breaking the problem down by first writing an outline.
       | 
       | Which we can all do at home and swap out the wikipedia articles
       | with our own data sets.
        
         | kingkongjaffa wrote:
         | I was able to mimic this in GPT with out the RAG component with
         | this custom instruction prompt, it does indeed write decent
         | content, better than other writing prompts I have seen.
         | 
         | PROMPT: create 3 diverse personas who would know about the user
         | prompt generate 5 questions that each persona would ask or
         | clarify use the questions to create a document outline, write
         | the document with $your_role as the intended audience.
        
       | dredmorbius wrote:
       | [delayed]
        
       ___________________________________________________________________
       (page generated 2024-09-17 23:00 UTC)