metadata

inference: false
license: mit
language:
  - en
metrics:
  - exact_match
  - f1
  - bertscore
pipeline_tag: text-classification

QA-Evaluation-Metrics

QA-Evaluation-Metrics is a fast and lightweight Python package for evaluating question-answering models. It provides various basic metrics to assess the performance of QA models. Check out our paper PANDA, a matching method going beyond token-level matching and is more efficient than LLM matchings but still retains competitive evaluation performance of transformer LLM models.

Installation

To install the package, run the following command:

pip install qa-metrics

Usage

The python package currently provides four QA evaluation metrics.

Exact Match

from qa_metrics.em import em_match

reference_answer = ["The Frog Prince", "The Princess and the Frog"]
candidate_answer = "The movie \"The Princess and the Frog\" is loosely based off the Brother Grimm's \"Iron Henry\""
match_result = em_match(reference_answer, candidate_answer)
print("Exact Match: ", match_result)
'''
Exact Match:  False
'''

Prompting LLM For Evaluation

Note: The prompting function can be used for any prompting purposes.

OpenAI

from qa_metrics.prompt_llm import *
set_openai_api_key(YOUR_OPENAI_KEY)
prompt = 'question: What is the Capital of France?\nreference: Paris\ncandidate: The capital is Paris\nIs the candidate answer correct based on the question and reference answer? Please only output correct or incorrect.'
prompt_gpt(prompt=prompt, model_engine='gpt-3.5-turbo', temperature=0.1, max_token=10)

'''
'correct'
'''

Anthropic

set_anthropic_api_key(YOUR_OPENAI_KEY)
prompt_claude(prompt=prompt, model_engine='claude-v1', anthropic_version="2023-06-01", max_tokens_to_sample=100, temperature=0.7)

'''
'correct'
'''

Transformer Match

Our fine-tuned BERT model is this repository. Our Package also supports downloading and matching directly. distilroberta, distilbert, and roberta are also supported now! 🔥🔥🔥

from qa_metrics.transformerMatcher import TransformerMatcher

question = "Which movie is loosley based off the Brother Grimm's Iron Henry?"
tm = TransformerMatcher("distilbert")
scores = tm.get_scores(reference_answer, candidate_answer, question)
match_result = tm.transformer_match(reference_answer, candidate_answer, question)
print("Score: %s; TM Match: %s" % (scores, match_result))
'''
Score: {'The Frog Prince': {'The movie "The Princess and the Frog" is loosely based off the Brother Grimm\'s "Iron Henry"': 0.88954514}, 'The Princess and the Frog': {'The movie "The Princess and the Frog" is loosely based off the Brother Grimm\'s "Iron Henry"': 0.9381995}}; TM Match: True
'''

F1 Score

from qa_metrics.f1 import f1_match,f1_score_with_precision_recall

f1_stats = f1_score_with_precision_recall(reference_answer[0], candidate_answer)
print("F1 stats: ", f1_stats)

match_result = f1_match(reference_answer, candidate_answer, threshold=0.5)
print("F1 Match: ", match_result)
'''
F1 stats:  {'f1': 0.25, 'precision': 0.6666666666666666, 'recall': 0.15384615384615385}
F1 Match:  False
'''

PANDA Match

from qa_metrics.pedant import PEDANT

question = "Which movie is loosley based off the Brother Grimm's Iron Henry?"
pedant = PEDANT()
scores = pedant.get_scores(reference_answer, candidate_answer, question)
max_pair, highest_scores = pedant.get_highest_score(reference_answer, candidate_answer, question)
match_result = pedant.evaluate(reference_answer, candidate_answer, question)
print("Max Pair: %s; Highest Score: %s" % (max_pair, highest_scores))
print("Score: %s; PANDA Match: %s" % (scores, match_result))
'''
Max Pair: ('the princess and the frog', 'The movie "The Princess and the Frog" is loosely based off the Brother Grimm\'s "Iron Henry"'); Highest Score: 0.854451712151719
Score: {'the frog prince': {'The movie "The Princess and the Frog" is loosely based off the Brother Grimm\'s "Iron Henry"': 0.7131625951317375}, 'the princess and the frog': {'The movie "The Princess and the Frog" is loosely based off the Brother Grimm\'s "Iron Henry"': 0.854451712151719}}; PANDA Match: True
'''

print(pedant.get_score(reference_answer[1], candidate_answer, question))
'''
0.7122460127464126
'''

If you find this repo avialable, please cite our paper:

@misc{li2024panda,
      title={PANDA (Pedantic ANswer-correctness Determination and Adjudication):Improving Automatic Evaluation for Question Answering and Text Generation}, 
      author={Zongxia Li and Ishani Mondal and Yijun Liang and Huy Nghiem and Jordan Lee Boyd-Graber},
      year={2024},
      eprint={2402.11161},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Updates

[01/24/24] 🔥 The full paper is uploaded and can be accessed here. The dataset is expanded and leaderboard is updated.
Our Training Dataset is adapted and augmented from Bulian et al. Our dataset repo includes the augmented training set and QA evaluation testing sets discussed in our paper.
Now our model supports distilroberta, distilbert, a smaller and more robust matching model than Bert!

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contact

For any additional questions or comments, please contact [[email protected]].