Using the Retrieval-Augmented Generation to Improve the Question-Answering System in Human Health Risk Assessment: The Development and Application
Electronics,
Год журнала:
2025,
Номер
14(2), С. 386 - 386
Опубликована: Янв. 20, 2025
While
large
language
models
(LLMs)
are
vital
for
retrieving
relevant
information
from
extensive
knowledge
bases,
they
always
face
challenges,
including
high
costs
and
issues
of
credibility.
Here,
we
developed
a
question
answering
system
focused
on
human
health
risk
using
Retrieval-Augmented
Generation
(RAG).
We
first
proposed
framework
to
generate
question–answer
pairs,
resulting
in
300
high-quality
pairs
across
six
subfields.
Subsequently,
created
both
Naive
RAG
an
Advanced
RAG-based
Question-Answering
(Q&A)
system.
Performance
evaluation
the
individual
research
subfields
demonstrated
that
outperformed
traditional
LLMs
(including
ChatGPT
ChatGLM)
RAG.
Finally,
integrated
module
single
subfield
launch
multi-knowledge
base
Our
study
represents
novel
application
technology
optimize
retrieval
methods
assessment.
Язык: Английский
Automatic Summarization Evaluation: Methods and Practices
Lecture notes in computer science,
Год журнала:
2025,
Номер
unknown, С. 169 - 181
Опубликована: Янв. 1, 2025
Язык: Английский
Outsourcing, Augmenting, or Complicating: The Dynamics of AI in Fact-Checking Practices in the Nordics
Emerging Media,
Год журнала:
2024,
Номер
2(3), С. 449 - 473
Опубликована: Сен. 1, 2024
The
practice
of
fact-checking
involves
using
technological
tools
to
monitor
online
disinformation,
gather
information,
and
verify
content.
How
do
fact-checkers
in
the
Nordic
region
engage
with
these
technologies,
especially
artificial
intelligence
(AI)
generative
AI
(GAI)
systems?
Using
theory
affordances
as
an
analytical
framework
for
understanding
factors
that
influence
technology
adoption,
this
exploratory
study
draws
on
insights
from
interviews
17
professionals
four
organizations.
Results
show
while
technologies
offer
valuable
functionalities,
remain
critical
cautious,
particularly
toward
AI,
due
concerns
about
accuracy
reliability.
Despite
acknowledging
potential
augment
human
expertise
streamline
specific
tasks,
limit
its
wider
use.
openness
integrating
advanced
but
emphasize
need
a
collaborative
approach
combines
strengths
both
humans
AI.
As
result,
GAI-based
solutions
are
framed
“enablers”
rather
than
comprehensive
or
end-to-end
solutions,
recognizing
their
limitations
replacing
augmenting
complex
cognitive
skills.
Язык: Английский