by sudoapps on 5/8/23, 5:48 PM with 86 comments
by furyofantares on 5/8/23, 7:49 PM
It has the same advantages search has over ChatGPT (being able to cite sources, being quite unlikely to hallucinate) and it has some of the advantages ChatGPT has over search (not needing exact query) - but in my experience it's not really in the new category of information discovery that ChatGPT introduced us to.
Maybe with more context I'll change my tune, but it's very much at the whim of the context retrieval finding everything you need to answer the query. That's easy for stuff that search is already good at, and so provides a better interface for search. But it's hard for stuff that search isn't good at, because, well: it's search.
by ftxbro on 5/8/23, 9:27 PM
To me this viewpoint looks totally alien. Imagine you have been training this model to predict the next token. At first it can barely interleave vowels and consonants. Then it can start making words, then whole sentences. Then it starts unlocking every cognitive ability one by one. It begins to pass nearly every human test and certification exam and psychological test of theory of mind.
Now imagine thinking at this point "training larger models with more data may not offer significant improvements" and deciding that's why you stop scaling it. That makes absolutely no sense to me unless 1) you have no imagination or 2) you want to stop because you are scared to make superhuman intelligence or 3) you are lying to throw off competitors or regulators or other people.
by Der_Einzige on 5/8/23, 8:18 PM
What these articles don't touch on is what to do once you've got the most relevant documents. Do you use the whole document as context directly? Do you summarize the documents first using the LLM (now the risk of hallucination in this step is added)? What about that trick where you shrink a whole document of context down to the embedding space of a single token (which is how ChatGPT is remembering the previous conversations). Doing that will be useful but still lossey
What about simply asking the LLM to craft its own search prompt to the DB given the user input, rather than returning articles that semantically match the query the closest? This would also make hybird search (keyword or bm25 + embeddings) more viable in the context of combining it with an LLM
Figuring out which of these choices to make, along with an awful lot more choices I'm likely not even thinking about right now, is what will seperate the useful from the useless LLM + Extractive knowledge systems
by orasis on 5/8/23, 8:00 PM
One trick is to have a LLM hallucinate a document based on the query, and then embed that hallucinated document. Unfortunately this increases the latency since it incurs another round trip to the LLM.
by Beltiras on 5/8/23, 8:47 PM
by chartpath on 5/8/23, 9:06 PM
We've done this in NLP and search forever. I guess even SQL query planners and other things that automatically rewrite queries might count.
It's just that now the parameters seem squishier with a prompt interface. It's almost like we need some kind of symbolic structure again.
by sudoapps on 5/8/23, 5:48 PM
by jeffchuber on 5/8/23, 10:07 PM
by iot_devs on 5/8/23, 10:41 PM
by pbhjpbhj on 5/8/23, 8:13 PM
>> “If you don't know the answer, just say that you don't know, don't try to make up an answer”
//
It seems silly to make this part of the prompt rather than a separate parameter, surely we could design the response to be close to factual. Then run a checker to ascertain a score for the factuality of the output?
by nico on 5/8/23, 8:59 PM
The model searches until it finds an answer, including distance and resolution
Search is performed by a DB, the query then sub-queries LLMs on a tree of embeddings
Each coordinate of an embedding vector is a pair of coordinate and LLM
Like a dynamic dictionary, in which the definition for the word is an LLM trained on the word
Indexes become shortcuts to meanings that we can choose based on case and context
Does this exist already?
by m3kw9 on 5/8/23, 9:42 PM
by A_D_E_P_T on 5/8/23, 11:42 PM
In this case, it can't possibly be approached. It certainly can't be attained.
Borges' Library of Babel, which represents all possible combinations of letters that can fit into a 400-page book, only contains some 25^1312000 books. And the overwhelming majority of its books are full of gibberish. The amount of "knowledge" that a LLM can learn or describe is VERY strictly bounded and strictly finite. (This is perhaps its defining characteristic.)
I know this is pedantic, but I am a philosopher of mathematics and this is a matter that's rather important to me.
by nadermx on 5/8/23, 9:01 PM
by flukeshott on 5/8/23, 10:29 PM