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

Improving recommendation systems and search in the age of LLMs

eugeneyan.com

Post reply on HN
Print view View original

81–90 of 98 posts

Re: Improving recommendation systems and search in the age of LLMs

#81

Post by LZ_Khan »

novia wrote: post #59

I started listening to this article (using a text to speech model) shortly after waking up. I thought it was very heavy on jargon. Like, it was written in a way that makes the author appear very intelligent without necessarily effectively conveying information to the audience. This is something that I've often seen authors do in academic papers, and my one published research paper (not first author) is no exception.…

I work in the field. The amount of jargon is indeed large but it's not out of the ordinary. It's simply how things are referred to. If the author explained what everything is the content would span a textbook.

That being said I do find the content difficult to understand, and I think reading the actual papers would be much more enlightening. But it's a great survey of all the things people have done.

Re: Improving recommendation systems and search in the age of LLMs

#82

Post by cco »

MostlyStable wrote: post #74
wildrhythms wrote: post #69

Earlier quoted context omitted.

No you don't understand, more queries = more engagement!

It's relatively easy to construct a scenario where more search is in fact indicative of better search. To stick with Spotify: let's imagine they have an amazing search tool that consistently finds new, interesting music that the user genuinely likes. I can imagine that in that situation, users are going to search more, because doing so consistently gets them new, enjoyable music. But the opposite is equally possible:…

Or more saves and thumbs up on signs resulting from a search is because users are desperate to save a song they like because they have no faith that they'll be able to find it again with search.

The only way is to use the product yourself and honestly engage with it. Stats can't answer this question.

Re: Improving recommendation systems and search in the age of LLMs

#83

Post by whatevertrevor »

MostlyStable wrote: post #74
wildrhythms wrote: post #69

Earlier quoted context omitted.

No you don't understand, more queries = more engagement!

It's relatively easy to construct a scenario where more search is in fact indicative of better search. To stick with Spotify: let's imagine they have an amazing search tool that consistently finds new, interesting music that the user genuinely likes. I can imagine that in that situation, users are going to search more, because doing so consistently gets them new, enjoyable music. But the opposite is equally possible:…

But isn't that actually the point? That measuring query volume tells you nothing?

Re: Improving recommendation systems and search in the age of LLMs

#84

Post by jimmyl02 »

MostlyStable wrote: post #74
wildrhythms wrote: post #69

Earlier quoted context omitted.

No you don't understand, more queries = more engagement!

It's relatively easy to construct a scenario where more search is in fact indicative of better search. To stick with Spotify: let's imagine they have an amazing search tool that consistently finds new, interesting music that the user genuinely likes. I can imagine that in that situation, users are going to search more, because doing so consistently gets them new, enjoyable music. But the opposite is equally possible:…

I feel like understanding this difference is what a good product manager should be responsible for. Not just optimizing any metric that is available but understanding the meaning behind them and choosing the push them the right direction.

Re: Improving recommendation systems and search in the age of LLMs

#85

Post by MostlyStable »

whatevertrevor wrote: post #83
MostlyStable wrote: post #74

Earlier quoted context omitted.

It's relatively easy to construct a scenario where more search is in fact indicative of better search. To stick with Spotify: let's imagine they have an amazing search tool that consistently finds new, interesting music that the user genuinely likes. I can imagine that in that situation, users are going to search more, because doing so consistently gets them new, enjoyable music. But the opposite is equally possible:…

But isn't that actually the point? That measuring query volume tells you nothing?

Yes, I was agreeing and expanding on the point.

Re: Improving recommendation systems and search in the age of LLMs

#86

Post by genewitch »

MostlyStable wrote: post #74
wildrhythms wrote: post #69

Earlier quoted context omitted.

No you don't understand, more queries = more engagement!

It's relatively easy to construct a scenario where more search is in fact indicative of better search. To stick with Spotify: let's imagine they have an amazing search tool that consistently finds new, interesting music that the user genuinely likes. I can imagine that in that situation, users are going to search more, because doing so consistently gets them new, enjoyable music. But the opposite is equally possible:…

Contextually unique searches versus contextually similar searches.

Nin, NIN, nine inch nails, Trent Reznor

VS

Nin, pantera, nail bomb, muse

This should be easy to differentiate, with a "[someone's name] distance algorithm" or such, right?

Re: Improving recommendation systems and search in the age of LLMs

#87

Post by a_bonobo »

Elicit has a nice new feature where given a research question, it seems to give the question to an LLM with the prompt to improve the question. It's a neat trick.

As an example, I gave it 'What is the impact of LLMs on search engines?' and it suggested three alternative searches under keywords, the keyword 'Specificity' has the suggested question 'How do large language models (LLMs) impact the accuracy and relevance of search engine results compared to traditional search algorithms?'

It's a really cool trick that doesn't take much to implement.

Re: Improving recommendation systems and search in the age of LLMs

#89

Post by anon8764352 »

@7d7n Eugene / others experienced in recommendation systems: for someone who is new to recommendation systems and uses variants of collaborative filtering for recommendations, what non-LLM approach would you suggest to start looking into? The cheaper the compute (ideally without using GPUs in the first place) the better, while also maximizing the performance of the system :)

Re: Improving recommendation systems and search in the age of LLMs

#90

Post by barrenko »

x1xx wrote: post #34

> Spotify saw a 9% increase in exploratory intent queries, a 30% rise in maximum query length per user, and a 10% increase in average query length—this suggests the query recommendation updates helped users express more complex intents To me it's not clear that it should be interpreted as an improvement: what I read in this summary is that users had to search more and to enter longer queries to get to what they neede…

People are just more and more used to interacting with an LLM / GPT, I think that's the why of the long questions + yes, people are not finding what they need.
Post reply on HN