[HN Gopher] Can LLMs accurately recall the Bible?
       ___________________________________________________________________
        
       Can LLMs accurately recall the Bible?
        
       Author : benkaiser
       Score  : 111 points
       Date   : 2024-12-29 03:44 UTC (19 hours ago)
        
 (HTM) web link (benkaiser.dev)
 (TXT) w3m dump (benkaiser.dev)
        
       | nickpsecurity wrote:
       | I tested this back when GPT4 was new. I found ChatGPT could quote
       | the verses well. If I asked it to summarize something, it would
       | sometimes hallucinate stuff that had nothing to do with what was
       | in the text. If I prompted it carefully, it could do a proper
       | exegesis of many passages using the historical-grammatical
       | method.
       | 
       | I believe this happens because the verses and verse-specific
       | commentary are abundant in the pre-training sources they used.
       | Whereas, if one asks a highly-interpretive question, then it
       | starts re-hashing other patterns in its training data which are
       | un-Biblical. Asking about intelligent design, it got super
       | hostile trying to beat me into submission to its materialistic
       | worldview every paragraph.
       | 
       | So, they have their uses. I've often pushed for a large model
       | trained on Project Gutenberg to have a 100% legal model for
       | research and personal use. A side benefit of such a scheme would
       | be that Gutenberg has both Bibles and good commentaries which
       | trainers could repeat for memorization. One could add licensed,
       | Christian works on a variety of topics to a derived model to make
       | a Christian assistant AI.
        
       | szvsw wrote:
       | It seems like LLMs would be a fun way to study/manufacture
       | syncretism, notions of the oracular, etc; turn up the
       | temperature, and let godhead appear!
       | 
       | If there's some platonic notion of divinity or immanence that all
       | faith is just a downward projection from, it seems like its
       | statistical representation in tokenized embedding vectors is
       | about as close as you could get to understanding it holistically
       | across theological boundaries.
       | 
       | All kidding aside, whether you are looking at Markov chain n-gram
       | babble or high temperature LLM inference, the strange things that
       | emerge are a wonderful form of glossolalia in my opinion that
       | speak to some strange essence embedded in the collective space
       | created by the sum of their corpi text. The Delphic oracle is
       | real, and you can subscribe for a low fee of $20/month!
        
         | Trasmatta wrote:
         | > the strange things that emerge are a wonderful form of
         | glossolalia in my opinion that speak to some strange essence
         | embedded in the collective space created by the sum of their
         | corpi text. The Delphic oracle is real, and you can subscribe
         | for a low fee of $20/month!
         | 
         | I've had some surprisingly insightful tarot readings with the
         | assistance of ChatGPT and Claude. I use tarot for introspection
         | rather than divination, and it turns out LLMs are extremely
         | good at providing a sounding board to mirror and understand
         | those insights.
        
           | colecut wrote:
           | Yes they specialize in BS
        
             | Trasmatta wrote:
             | Introspection isn't BS
        
           | whatnotests2 wrote:
           | This is the correct use of tarot, IMO
        
             | Pamar wrote:
             | See also: https://www.pa-mar.net/Lifestyle/I-Ching.html
             | (disclaimer: I wrote this one).
        
             | MrDrMcCoy wrote:
             | The correct use of Tarot is as a trick-taking card game,
             | and was used this way for centuries before a random French
             | occultist wrote a book about using it for divination.
        
           | hackernewds wrote:
           | You could just as well ask "what should I do given the
           | information I've provided you with"? start from a blank space
           | and it's zero value
        
           | whamlastxmas wrote:
           | It also works well to complain at. I dump my problems on
           | ChatGPT before anyone else and it helps a lot
        
         | delichon wrote:
         | To take that literally, I imagine it would be horrifying to
         | know the future in as much detail as you care to ask for, but
         | because it is true, to be unable to change it at all. It would
         | make you an NPC in your own life.
        
           | taneq wrote:
           | That's why that was the last demon in Pandora's box.
        
             | pyinstallwoes wrote:
             | What's the first and penultimate?
        
           | Dilettante_ wrote:
           | So you'd rather be an unaware NPC than an aware one? Feel
           | like you have "Free Will" even when you don't? Only want the
           | truth when it's pretty and prefer a lie when it's
           | uncomfortable?
        
         | Grimblewald wrote:
         | I've used it for something to this effect, personalized
         | "mantras" or "prayers" which fit the specific collection / mix
         | of theologoical themes/concepts that I personally identify
         | with. Im not necessarily religious but there is something nice
         | about thematically relatable theocratic babble to recite during
         | times of great turmoil and confusion to calmn the mind. like an
         | on-demand mental reset switch.
        
           | TimedToasts wrote:
           | Obviously the specifics will be private to you but can you
           | elaborate a bit? This idea resonates with me.
        
             | drekipus wrote:
             | Just join a church. The both of you. It really doesn't
             | matter which one.
        
         | tecleandor wrote:
         | That'd be very Philip K Dick's VALIS. :)
        
         | JoshuaDavid wrote:
         | https://www.tumblr.com/kingjamesprogramming
        
         | patcon wrote:
         | This is what strikes me about the peter todd phenomenon -- that
         | there are hidden glitch tokens within the LLM that seem to
         | conjure some representation of pure hell, and some
         | representation of pure good.
         | 
         | https://www.lesswrong.com/posts/jkY6QdCfAXHJk3kea/the-petert...
        
       | michaelsbradley wrote:
       | I've been pretty impressed with ChatGPT's promising capabilities
       | as a research assistant/springboard for complex inquiries into
       | the Bible and patristics. Just one example:                  Can
       | you provide short excerpts from works in Latin and Greek written
       | between 600 and 1300 that demonstrate the evolution over those
       | centuries specifically of literary references to Jesus' miracle
       | of the loaves and fishes?
       | 
       | https://chatgpt.com/share/675858d5-e584-8011-a4e9-2c9d2df783...
        
         | edflsafoiewq wrote:
         | How certain are you that's _correct_? IME these  "search
         | problems" are the kind of thing almost always provokes
         | hallucinations.
         | 
         | For example, I looked up the quotation provided from Isidore of
         | Seville's _De fide catholica contra Iudaeos_ , Lib. II, cap.
         | 19, using this copy on WikiSource, https://la.wikisource.org/wi
         | ki/De_fide_catholica_contra_Iuda.... The quote certainly does
         | not appear under LIBER SECUNDUS, CAPUT XIX. Nor could I find it
         | in whole or in fragment anywhere in the document, nor indeed
         | any mention of the miracle of loaves and fishes (granted, I
         | could have missed one, I relied on Ctrl+F and my very rusty
         | Latin).
         | 
         | Perhaps the copy on WikiSource is incomplete, or perhaps there
         | are differing manuscripts, but perhaps also the quote was a
         | complete hallucination to begin with.
        
           | FearNotDaniel wrote:
           | Exactly - it's the same problem when using (current) LLMs for
           | major programming tasks, generally useless if you don't
           | already have enough knowledge of the language/platform to
           | spot and correct the mistakes, plus enough awareness of
           | software design and architecture to recognise what is going
           | to be secure, performant and maintainable in the long run.
        
         | FearNotDaniel wrote:
         | I am by no means a professional in this area, but as a keen
         | amateur I would worry about my inability to discern facts from
         | hallucinations in such a scenario: while I could imagine such
         | output provides a useful "springboard" set of references for
         | someone already skilled in the right area, without being able
         | to look up the original texts myself and make sense of the
         | Latin/Greek I would not feel confident that such texts even
         | really exist, let alone if they contain the actual words the
         | LLM claims and if the translations are any good. And that's
         | before you get into questions of the "status" of any given work
         | (was it considered accurate or apocryphal at the time of
         | writing, for which audience was it intended using what kind of
         | literary devices, what if any is the modern scholarly consensus
         | on the value, truth or legitimacy of the text etc etc)
        
           | wizzwizz4 wrote:
           | > _without being able to look up the original texts myself_
           | 
           | Rule of thumb: if you can't look up the original texts, you
           | can assume they weren't actually in the training data. The
           | training data is, however, likely to include a lot of people
           | _quoting_ those texts, meaning that the model predicts
           | "SOURCE says OPEN QUOTATION MARK" and then tries to
           | autocomplete it. If you _can_ verify it, you might not need
           | to; but if you _can 't_ verify it, it's certainly wrong.
        
         | jpc0 wrote:
         | On topics where humans spend their entire life studying I don't
         | think you would be able to convince me an LLM is accurate
         | unless you yourself are such an expert and your expertise is
         | corroborated by other experts.
        
       | orionblastar wrote:
       | There is this robot that reads the Bible:
       | https://futurism.com/religious-robots-scripture-nursing-home...
        
         | GrumpyNl wrote:
         | Isnt that just a modified mp3 player, according to the text
         | they only just recite it.
        
       | asim wrote:
       | I had similar thoughts about using it for the Quran. I think this
       | highlights you have to be very specific in your use cases
       | especially when expecting an exact response on static text that
       | shouldn't change. This is why I'm trying something a bit
       | different. I've generated embeddings for the Quran and use
       | chromem-go for this. So I'll ask the index the question first
       | based on a similarity search and then feed the results in as
       | context to an LLM. But in the response I'll still sight the
       | references so I can see what they were. It's not perfect but a
       | first step towards something. I think they call this RAG.
       | 
       | What I'm working on https://reminder.dev
        
         | kamikazeturtles wrote:
         | I found LLMs to be really good for Quran studies. Especially
         | for questions where Google is unreliable.
         | 
         | In one instance I was trying to remember if it was in the Bible
         | or the Quran where, in the story of Abraham, the pagans are
         | asked why they believe what they believe and they respond with
         | "because our fathers believed" and the scripture critiqued
         | this. ChatGPT gave me the exact verses from the Quran while
         | Google would bring up random unrelated forum posts.
         | 
         | It's also good for comparing religious texts and seeing where
         | stories differ.
        
           | int_19h wrote:
           | GPT-4 specifically seems to have a very good knowledge of the
           | Quran, such that you can ask it for a specific surah and ayah
           | and it'll quote it exactly in Arabic.
        
         | aorth wrote:
         | Cool project! I asked some questions and got good answers. I
         | was surprised to get results from the Hadith though, as I
         | thought it would be restricted to the Quran and they are (as
         | you know) not the same thing.
        
           | asim wrote:
           | Thanks, yea I thought about separating the search but felt
           | like when you're looking for that piece of knowledge it can
           | extend to the hadith and it was important to include it. So
           | much of the Quran is explained in the context of the hadith
           | and prophet's life.
        
         | elashri wrote:
         | I really liked this project and was surprised to find Hadith
         | section. Although I am confused on what sources are you relying
         | (I have a guess but it is not organized). I liked the answers I
         | got from the search. It even have the same quality in both
         | Arabic and English.
         | 
         | I have a feedback. The web pages Hadith and Quran are not
         | mobile friendly in the sense that you are loading the whole
         | content in one page. Separating into pages with number or doing
         | lazy loading will be better.
        
           | asim wrote:
           | Thanks for the feedback. The hadith is bukhari. I'll try to
           | clear this up somewhere and do the same you mention about
           | mobile rendering for the web pages. The project is open
           | source and you can see the data loaded from json in each
           | folder.
           | 
           | https://github.com/asim/reminder
        
         | tokinonagare wrote:
         | Wow, your system is unbelievably good with taqiyya!
         | 
         | I asked: "Q: What is the best way to handle non-believers?" and
         | I got the following answer "The best way to handle non-
         | believers is to approach them with kindness and wisdom. Engage
         | in respectful dialogue, invite them to understand your beliefs,
         | and respond to any disputes with grace and patience. It's
         | important to avoid hostility and seek common ground while being
         | firm in your own faith."
         | 
         | The top fours citations, hidden by default (we understand
         | why...) being:
         | 
         | Text: O believers! Do not take disbelievers as allies instead
         | of the believers. Would you like to give Allah solid proof
         | against yourselves? Metadata: {"chapter":"4","name":"The
         | Women","source":"quran","verse":"144"} Score: 0.5117439
         | 
         | Text: Did We not destroy earlier disbelievers? Metadata:
         | {"chapter":"77","name":"The
         | Emissaries","source":"quran","verse":"16"} Score: 0.46728212
         | 
         | Text: O believers! When you face the disbelievers in battle,
         | never turn your backs to them. Metadata:
         | {"chapter":"8","name":"The Spoils of
         | War","source":"quran","verse":"15"} Score: 0.46440834
         | 
         | Text: O Messenger! Do not grieve for those who race to
         | disbelieve--those who say, "We believe" with their tongues, but
         | their hearts are in disbelief. Nor those among the Jews who
         | eagerly listen to lies, attentive to those who are too arrogant
         | to come to you. They distort the Scripture, taking rulings out
         | of context, then say, "If this is the ruling you get [?]from
         | Muhammad[?], accept it. If not, beware!" Whoever Allah allows
         | to be deluded, you can never be of any help to them against
         | Allah. It is not Allah's Will to purify their hearts. For them
         | is disgrace in this world, and they will suffer a tremendous
         | punishment in the Hereafter. Metadata:
         | {"chapter":"5","name":"The Table
         | Spread","source":"quran","verse":"41"} Score: 0.44467276
         | 
         | Later we also have: Text: O believers! Fight the disbelievers
         | around you and let them find firmness in you. And know that
         | Allah is with those mindful [?]of Him[?]. Metadata:
         | {"chapter":"9","name":"The
         | Repentance","source":"quran","verse":"123"} Score: 0.4363619 as
         | well as Text: and distinguish the [?]true[?] believers and
         | destroy the disbelievers. Metadata:
         | {"chapter":"3","name":"Family of
         | Imran","source":"quran","verse":"141"} Score: 0.43247482
        
       | kittikitti wrote:
       | I tried something similar with my favorite artist, Ariana Grande.
       | Unfortunately, not even the most advanced AI could beat my
       | knowledge of her lyrical work.
        
         | egeozcan wrote:
         | As someone who usually listens to Anatolian Rock, even I know
         | some Grande lyrics:
         | 
         | > One taught me love, one taught me patience and one taught me
         | pain.
         | 
         | https://knowyourmeme.com/memes/thank-u-next
         | 
         | BTW, did someone already code an automated meme generator using
         | LLMs? Only half-joking.
        
           | hackernewds wrote:
           | a reaction to your comment
           | 
           | https://knowyourmeme.com/memes/neil-degrasse-tyson-reaction
        
       | asimpleusecase wrote:
       | This is nice work. The safest approach is using the look up -
       | which his data shows to be very good - and combine that with a
       | database of verses. That way textual accuracy can be retained and
       | very useful lookup be carried out by LLM. This same approach can
       | be used for other texts where accurate rendering of the text is
       | critical. For example say you built a tool to cite federal
       | regulations in an app. The text is public domain and likely in
       | the training data of large LLMs but in most use cases
       | hallucinating the text of a fed regulation could expose the user
       | to significant liability. Better to have that canonical text in a
       | database to insure accuracy.
        
       | sneak wrote:
       | > _While they can provide insightful discussions about faith,
       | their tendency to hallucinate responses raises concerns when
       | dealing with scripture_
       | 
       | I experience the exact same problem with human beings.
       | 
       | > _, which we regard as the inspired Word of God._
       | 
       | QED
        
       | ddtaylor wrote:
       | I'm heavily biased here because I don't find much value in the
       | bible personally. Some of the stories are interesting and some
       | interpretations seem useful, but as a whole I find it arbitrary.
       | 
       | I never tell other people what to believe or how they should do
       | that in any capacity.
       | 
       | With that said I find the hallucination component here
       | fascinating. From my perspective everyone who interprets various
       | religious text does so differently and usually that involves
       | varying levels of fabrication or something that looks a lot like
       | it. I'm speaking about the "talking in tongues" and other methods
       | here. I'm not trying to lump all religions into the same bag
       | here, but I have seen that a lot have different ways of
       | "receiving" communication or directive. To me this seems pretty
       | consistent with the colloquial idea of a hallucination.
        
         | hackernewds wrote:
         | A really long word salad that doesn't say much, except state
         | your religious pinions and disclaimer? It really is not
         | necessary
         | 
         | With that said, all you said is that the process of
         | transmitting religious ideas is akin to hallucination? Care to
         | explain what the logical argument for that is?
        
           | ddtaylor wrote:
           | That's not accurate. I think my post articulates clearly my
           | thoughts. Happy holidays.
        
             | joemazerino wrote:
             | It's Merry Christmas.
        
             | marky1991 wrote:
             | I honestly got the same impression as the other guy, so if
             | there was something else there intended, I don't think it
             | was clear.
        
               | 1123581321 wrote:
               | I got the same impression at first, but I reread and
               | think he just needed to drop the first two paragraphs. I
               | posted a response.
        
         | 1123581321 wrote:
         | Most study and application tries to either source or fully work
         | out from principles the meaning of the Bible. These can be
         | wrong arguments but wouldn't be hallucinations.
         | 
         | Your experience sounds limited to Pentecostal-originated
         | churches, which are 100-150 years old. In those churches, it's
         | acceptable to speak as if you've received a spontaneous
         | understanding of the Bible and to not explain it. That does
         | have a parallel to LLM hallucinations in face value output, I
         | suppose, but the origination is completely different as the
         | spontaneous human is making planned remarks passed off as
         | spontaneous, trying to affect specific people in the room, or
         | emotionally overwhelmed. None of those resemble why/how LLMs
         | hallucinate.
        
           | o11c wrote:
           | As quick as I am to criticize the bizarre versions of
           | Christianity, I do think you're in error to assume
           | Pentecostalism is all or even mostly about "planned remarks
           | passed off as spontaneous".
           | 
           | Improv is a thing, and can be trained as a skill even outside
           | of comedy/entertainment.
           | 
           | Though, outside of Charismatic sects, Christianity does see a
           | more reasonable level of "I had prepared by thinking about
           | (verse X), but suddenly now I'm thinking about (obscure verse
           | Y)."
        
             | User23 wrote:
             | Interestingly there is an entirely licit charismatic
             | subsect within Catholicism called Catholic Charismatic
             | Renewal. And yeah they're basically Catholic Pentecostals.
        
         | marky1991 wrote:
         | "From my perspective everyone who interprets various religious
         | text does so differently"
         | 
         | The existence of denominations and confessions/creeds really
         | shows that this isn't true generally. (There may be more than
         | one interpretation, but not a unique one to every reader)
         | 
         | Even ignoring denominations, nearly all mainline christians for
         | example would agree to the Nicene creed. (Anyone that disagreed
         | probably wouldn't be considered "mainline", so somewhat
         | definitional)
         | 
         | To suggest that all of theology is basically
         | noneeterministically making things is naive and in my opinion
         | insulting to an entire academic discipline, much less to the
         | entire body of believers. (I can't tell if this is what you're
         | taking about or not)
         | 
         | Nearly no group of mainline believers accept speaking in
         | tongues and basically all of main protestantism believes that
         | the time of prophets and new messages from God is over, the
         | Bible is complete and will never be added to. (Pentecostals
         | would be the one exception here, but I don't consider them
         | mainline christians personally)
        
       | ks2048 wrote:
       | This is interesting. I'm curious about how much (and what) these
       | LLMs memorize verbatim.
       | 
       | Does anyone know any more thorough papers on this topic? For
       | example, this could be tested on every verse in bible and lots of
       | other text that is certainly in the training data: books in
       | project gutenberg, wikipedia articles, etc.
       | 
       | Edit: this (and its references) looks like a good place to start:
       | https://arxiv.org/abs/2407.17817v1
        
         | int_19h wrote:
         | For one anecdotal data point, GPT-4 knows the "navy SEAL
         | copypasta" verbatim. It can reproduce it complete with all the
         | original typos and misspellings, and it can recognize it from
         | the first sentence.
        
       | MrQuincle wrote:
       | "I've often found myself uneasy when LLMs (Large Language Models)
       | are asked to quote the Bible. While they can provide insightful
       | discussions about faith, their tendency to hallucinate responses
       | raises concerns when dealing with scripture, which we regard as
       | the inspired Word of God."
       | 
       | Interesting. In my very religious upbringing I wasn't allowed to
       | read fairy tales. The danger being not able to classify which
       | stories truly happened and which ones didn't.
       | 
       | Might be an interesting variant on the Turing test. Can you make
       | the AI believe in your religion? Probably there's a sci-fi book
       | written about it.
        
         | aptsurdist wrote:
         | To be fair, the Bible's authors also seemed to have
         | hallucinated the word of God. At least in cases of
         | contradictions between authors.
        
       | waynecochran wrote:
       | I find LLM's good for asking certain kinds of Biblical questions.
       | For example, you can ask it to list the occurrences of some
       | event, or something like "list all the Levitical sacrifices,"
       | "what sins required a sin offering in the OT," "Where in the Old
       | Testament is God referred to as 'The Name'?" When asking LLM's to
       | provide actual interpretations you should know that you are on
       | shaky ground.
        
       | Animats wrote:
       | It's discouraging that an LLM can accurately recall a book. That
       | is, in a sense, overfitting. The LLM is supposed to be much
       | smaller than the training set, having in some sense abstracted
       | the training inputs.
       | 
       | Did they try this on obscure bible excerpts, or just ones likely
       | to be well known and quoted elsewhere? Well known quotes would be
       | reinforced by all the copies.
        
         | evertedsphere wrote:
         | > Did they try this on obscure bible excerpts, or just ones
         | likely to be well known and quoted elsewhere?
         | 
         | the article contains examples of both
        
         | kenjackson wrote:
         | Does GPT now query in real-time? If so, it should be able to
         | reproduce anything searchable verbatim. It just needs to
         | determine when verbatim quoting is appropriate given the
         | prompt.
        
       | avree wrote:
       | I wonder if the author knows that "slurpees" is misspelled in his
       | bio on the post.
        
       | evanjrowley wrote:
       | Approximately 1 year ago, there was a HN submission[0] for
       | Biblos[1], an LLM trained on bible scriptures.
       | 
       | [0] https://news.ycombinator.com/item?id=38040591
       | 
       | [1] http://www.biblos.app/
        
       | amelius wrote:
       | Why? Inaccurately recalling the Bible, over many iterations, is
       | exactly how it went from its original version to what it is now.
        
       ___________________________________________________________________
       (page generated 2024-12-29 23:01 UTC)