Teach your LLM to answer with facts, not fiction
blog.myscale.com
Teach your LLM to answer with facts, not fiction
1–10 of 149 posts
Re: Teach your LLM to answer with facts, not fiction
#2Situation: people try to use these predictive text chatbots as search engines.
Problem: LLMs are not search engines. They extrapolate, interpolate, and approximate (so-called “hallucinations”) so they can always produce somewhat-plausible text completions.
Solution: Create a search engine so good at returning relevant results that even an LLM can make use of it… then go to significant lengths to plug that search engine into the LLM, preventing people from reading the search results directly.
Why not simply give people access to the search engine‽ People know how to use search engines!! This is the fifth time I've seen an article like this, and I'm still… baffled. It's https://xkcd.com/2021/ all over again.
Re: Teach your LLM to answer with facts, not fiction
#3It is not a good start that they begin with a dictionary definition of Hallucinations. While the similarities to what a LLM does are apparent enough for the term to be used, LLMs are under no obligation to behave similar to the dictionary definition of Hallucinations.
In general facts are not the answer to Hallucinations. You can't possibly have every fact for every situation. The true solution to Hallucinations is figuring out how to make a model say 'I don't know"
Re: Teach your LLM to answer with facts, not fiction
#4It is not a good start that they begin with a dictionary definition of Hallucinations. While the similarities to what a LLM does are apparent enough for the term to be used, LLMs are under no obligation to behave similar to the dictionary definition of Hallucinations. In general facts are not the answer to Hallucinations. You can't possibly have every fact for every situation. The true solution to Hallucinations is f…
You cannot fix what you cannot measure, here is an attempt to do just that with HallMeter https://why.network/
Still have to figure a measurement unit.
Re: Teach your LLM to answer with facts, not fiction
#5I believe that LLMs should be banned, but if they have to exist, we should teach them ethics first before anything else.
Re: Teach your LLM to answer with facts, not fiction
#6It is not a good start that they begin with a dictionary definition of Hallucinations. While the similarities to what a LLM does are apparent enough for the term to be used, LLMs are under no obligation to behave similar to the dictionary definition of Hallucinations. In general facts are not the answer to Hallucinations. You can't possibly have every fact for every situation. The true solution to Hallucinations is f…
This article suggests that LLMs should use a database as a reference for factual information. Rather than asking LLMs to provide their own answers, it is recommended that they summarize based on the facts extracted from the database. This approach reduces the likelihood of hallucinations among LLMs.
Re: Teach your LLM to answer with facts, not fiction
#7Situation: people try to use these predictive text chatbots as search engines. Problem: LLMs are not search engines. They extrapolate, interpolate, and approximate (so-called “hallucinations”) so they can always produce somewhat-plausible text completions. Solution: Create a search engine so good at returning relevant results that even an LLM can make use of it… then go to significant lengths to plug that search engi…
Yea… my opinion on this is that startups are attempting to force a market for chat bots, instead of accepting that LLM embeddings are best utilized as a search feature, not new product surface area
Re: Teach your LLM to answer with facts, not fiction
#8It is not a good start that they begin with a dictionary definition of Hallucinations. While the similarities to what a LLM does are apparent enough for the term to be used, LLMs are under no obligation to behave similar to the dictionary definition of Hallucinations. In general facts are not the answer to Hallucinations. You can't possibly have every fact for every situation. The true solution to Hallucinations is f…
This article suggests that LLMs should use a database as a reference for factual information. Rather than asking LLMs to provide their own answers, it is recommended that they summarize based on the facts extracted from the database. This approach reduces the likelihood of hallucinations among LLMs.
> This approach reduces the likelihood of hallucinations among LLMs.
This has not been my experience. Did you create any benchmarks as a part of this project?
Re: Teach your LLM to answer with facts, not fiction
#9Situation: people try to use these predictive text chatbots as search engines. Problem: LLMs are not search engines. They extrapolate, interpolate, and approximate (so-called “hallucinations”) so they can always produce somewhat-plausible text completions. Solution: Create a search engine so good at returning relevant results that even an LLM can make use of it… then go to significant lengths to plug that search engi…
Well, search engines and my ability to query them aren't good enough for highly specific or poorly worded questions yet. LLMs are sometimes better in this space.
Re: Teach your LLM to answer with facts, not fiction
#10would be nice if they could show a gradient score on results that show how certain it is of its answers...
It should be fairly trivial for it to tell you how often its straight up lied about something.