Large Language Models (LLMs) are highly effective for various "reading" tasks, where the output is typically shorter than or similar in length to the input prompt, offering significant efficiency gains in processing and understanding text.
Mind Map
Klik untuk perbesar
Klik untuk menjelajahi mind map interaktif lengkap
in the last video we looked at writing
tasks where you would specify a prompt
to the LA L model and have it generate a
comparatively longer output than the
input prompt it turns out LMS also
useful for many reading task and by that
I mean task where you would input a
prompt and then have it generate usually
a similar length or often shorter output
than the input prompt let's take a look
at some reading tasks starting with
something I use myself all the time
which is proof reading many times if I'm
writing a piece of text I will read
through it carefully three or four times
myself for spelling and grammatical
errors and even though I thought I Pro
read carefully myself a l language model
we'll still find errors in it that
somehow I had missed here's an example
of a prompts that you could try proof
read the following text and I find that
if you tell it what you want the text
before so here's text intended for
website selling TR of toys and sometimes
ask it to check for spelling and
grammatical errors as well as awkward
sentences and then have it rewrited with
corrections and this is a piece of text
with some errors and the output of the
launch language model fixes snuggle was
misspelled and it fixes this little
piece of grammar over here when I'm
writing text myself that I want to be
quite confident is free of spelling and
grammatical errors and sometimes also
awkward sentences I actually use this
myself to proof read what I write a
second reading task that large languish
models are often used for is to
summarize long articles one of my
collaborators Eric Brinson who's a sord
professor once sent me an email linking
to an article that he had written titled
the tour ring trap and I knew it was a
good article but it was a very long
article and I didn't have time to read
the whole thing before I responded to
his email so I actually used the
following prompt and copy pasted his
entire article into an web interface of
a large langage model and had it quickly
generate a summary for me it turns out
this paper that he had written talks
about how human like AI offers benefits
but there's a lot to be done by having
AI augment humans rather than automate
but the point of brov's article on the
touring trap was he was advocating that
instead of having AI automate or replace
human work we should put more effort
into having AI complement augment human
work and so with a lar action model
summarizing this long article I was able
to get back on this faster than if I had
to read the entire article myself and by
the way this is a good article
eventually I did read the entire article
myself and really enjoyed it but today I
do sometimes use large language models
to summarize for me things that I don't
have time to read in this entirety and
so this is a use case that you could go
to one of the web interfaces of a lar
language model and use relatively
quickly yourself
now it turns out there's a software
application version of this too that is
taking off in businesses let me
illustrate this with an example say
you're a manager of a customer service
call center where you have many customer
service agents like this person shown on
the left with the microphone having
phone calls with customers like this
person shown on the right if you have
permission to record these phone calls
between the agents and the customers you
can then run the phone calls through a
speech recognition system to get a text
transcript of the conversation and if
you have many customer service agents
having conversations you end up with a
lot of text transcripts if you want to
review what's going on in your call
center you priority end up with too much
text to read given a text transcript
like this between a customer and an
agent you what really happened in this
call one use of lar language models
would be to have it summarize this
entire conversation and generate a short
summary like mk41 127 KX was reward is
broken and so on and if you were to take
all of these different text transcripts
and have a software application to
generate these summaries then you as the
manager of this can take a quick look at
all of these summaries and just maybe
spots if there are any issues or any
trends that you want to be aware of a
system like this would be implemented as
a software application that uses a large
language model because it doesn't really
make sense for you or anyone else to
copy paste these conversations one at a
time into the website of a large
language model provider in terms of
customer service interactions L langage
models are also used for customer email
analysis in an earlier video you saw the
example of taking a customer email and
deciding if is a complaint um in this
case no as well as what department to
Route this email and this will be
another software application that uses a
l language model let's take a deeper
look at how one could build this
application focusing on the parts of
deciding what department to Route this
email one thing you could do is writeit
prompt to tell the L to read the email
and decide which department to Route it
to so you can specify the task and
provide the email but it turns out that
with a prompt like this you may find
that the algorithm routes it to the
complaints department in this case which
may or may not be a department that
exists in your organization
so this would be an example of where the
L has been given insufficient context to
know what are the names of the actual
departments in your company that they
should choose from in contrast if you
were to update the promise follows we
say read the email choose the most
appropriate Department to Rouse it to
and choose Department only from the
following list in this case given the
set of choices you wanted to choose from
routs it to the apparel Department
correctly it process of building an
application using the launch n model is
again not at all in commmon to write a
prompt that doesn't quite work right the
first time and when you find it routs it
to a non-existent complaint department
then just update the prompt and that
fixes the problem one last application I
want to touch on is reputation
monitoring where you can use an LM to
build a dashboard to track your customer
sentiment positive or negative of your
business or your products over time so
for example if you run a restaurant and
occasionally your customers write online
reviews or send you emails describing
their experience you can then use a
prompt like this read the following
review and classify as having the
positive negative sentiment to have it
decide automatically if each review was
positive or negative so in this case if
the food was amazing or service are
friendly that would be classified as
having a positive sentiment then by
having software counts the number of
positive reviews per day as well as the
number of negative negative reviews per
day you can build a dashboard that
tracks per day over time how the
sentiments are trending and looks like
the customer senent is pretty positive
but if ever it starts trending negative
like this with more negative reviews
then this dashboard can alert you to
that maybe something's happening that we
should pay attention to and see if
there's something we need to fix at the
restaurant so in this video we looked at
a number of reading applications
including proof reading summarization
email routing restaurant review sens
analysis if you can think of task where
you wish you had someone that could read
a piece of text and just say a few
things or give a few quick indications
of what was in that piece of text that
could be a good candidate for a reading
toss to get home to do for you next
let's go to the next video to take a
Klik teks atau cap waktu mana pun untuk melompat ke momen tersebut dalam video
Bagikan:
Sebagian besar transkrip siap dalam waktu kurang dari 5 detik
Salin Satu Klik125+ BahasaCari KontenLoncat ke Cap Waktu
Tempel URL YouTube
Masukkan link video YouTube apa saja untuk mendapatkan transkrip lengkap
Formulir Ekstraksi Transkrip
Sebagian besar transkrip siap dalam waktu kurang dari 5 detik
Pasang Ekstensi Chrome Kami
Dapatkan transkrip seketika tanpa meninggalkan YouTube. Pasang ekstensi Chrome kami untuk akses satu klik ke transkrip video apa pun langsung di halaman tontonan.
