FactScore is an automatic evaluation metric for factual precision in long-form text generation. It uses large language models and retrieval to break down generations into atomic facts and then measure the correctness with respect to a knowledge source (like Wikipedia).
Project description
FActScore
This is the official release accompanying our preprint, "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation". FActScore is available as a PIP package as well.
Install
Make a new Python 3.7+ environment using virtualenv
or conda
.
pip install factscore
python -m spacy download en_core_web_sm
Download the data
python -m factscore.download_data
Or, download it manually from this Google Drive link. Make a cache directory .cache/factscore
, and place unzipped demos
and enwiki-20230401.db
in that directory.
Running FactScore
python -m factscore.factscorer --data_path {data_path} --model_name {estimator_name} --cache_dir {cache_dir} --openai_key {openai_key}
data_path
can be something likedata/src-light/bio_ChatGPT_v0.2.jsonl
which is in a format we have been using so far. TODO for simplying the format and allowing it to take any topics/generations.model_name
:retrieval+ChatGPT
,retrieval+ChatGPT+npm
, two more configs (retrieval+llama
,retrieval+llama+npm
) coming soon!cache_dir
:.cache/factscore
by default.openai_key
: File containing API Key, needed when ChatGPT is being used.
For example,
python -m factscore.factscorer \
--data_path original_generation/v0.2/answers_mpt-7b_bio_test_addtional.jsonl \
--model_name "retrieval+ChatGPT" \
--cache_dir ".cache/factscore" \
--openai_key "api.key"
It uses enwiki-20230401
by default, and will download the database from our Google drive.
Instructions to use Instruct-LLAMA-7B or your own LM coming soon!
To use a custom knowledge source.
You need a .jsonl
file where each line is a dictionary containing title
and text
. text
can either be a string or a list of strings (e.g., sections).
from factscore.factscorer import FactScorer
fs = FactScorer()
# this will create a database using your file
# for English Wikipedia (18GB)), it takes ~8 hours
# once DB file is created, you can reuse it by only specifying `db_path`
fs.register_knowledge_source(name_of_your_knowledge_source,
data_path=path_to_jsonl_file,
db_path=path_to_output_db_file)
# now, when you compute a score, specify knowledge source to use
score = fs.get_score(topics, generations, knowledge_source=name_of_your_knowledge_source)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for factscore-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f67a8b5327c17c8eb231c4ae5ce9283db5d2488a408b0e0a8104d10457c41862 |
|
MD5 | 64e9336e5647168ba9c0c3bf39d11f5e |
|
BLAKE2b-256 | ef0ed3a155e8a62d698307471470b7820a68b57a7d5aa96ec55575ae59d00ffd |