desc + bib

parapluie.py

@@ -19,16 +19,36 @@ import datasets
 
 # TODO: Add BibTeX citation
 _CITATION = """\
-@InProceedings{huggingface:module,
-title = {A great new module},
-authors={huggingface, Inc.},
-year={2020}
+@inproceedings{lemesle-etal-2025-paraphrase,
+    title = "Paraphrase Generation Evaluation Powered by an {LLM}: A Semantic Metric, Not a Lexical One",
+    author = "Lemesle, Quentin  and
+      Chevelu, Jonathan  and
+      Martin, Philippe  and
+      Lolive, Damien  and
+      Delhay, Arnaud  and
+      Barbot, Nelly",
+    editor = "Rambow, Owen  and
+      Wanner, Leo  and
+      Apidianaki, Marianna  and
+      Al-Khalifa, Hend  and
+      Eugenio, Barbara Di  and
+      Schockaert, Steven",
+    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
+    month = jan,
+    year = "2025",
+    address = "Abu Dhabi, UAE",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2025.coling-main.538/",
+    pages = "8057--8087",
+    abstract = "Evaluating automatic paraphrase production systems is a difficult task as it involves, among other things, assessing the semantic proximity between two sentences. Usual measures are based on lexical distances, or at least on semantic embedding alignments. The rise of Large Language Models (LLM) has provided tools to model relationships within a text thanks to the attention mechanism. In this article, we introduce ParaPLUIE, a new measure based on a log likelihood ratio from an LLM, to assess the quality of a potential paraphrase. This measure is compared with usual measures on two known by the NLP community datasets prior to this study. Three new small datasets have been built to allow metrics to be compared in different scenario and to avoid data contamination bias. According to evaluations, the proposed measure is better for sorting pairs of sentences by semantic proximity. In particular, it is much more independent to lexical distance and provides an interpretable classification threshold between paraphrases and non-paraphrases."
 }
 """
 
 # TODO: Add description of the module here
 _DESCRIPTION = """\
-This new module is designed to solve this great ML task and is crafted with a lot of care.
+ParaPLUIE is a metric for evaluating the semantic proximity of two sentences. 
+ParaPLUIE use the perplexity of an LLM to compute a confidence score.
+It has shown the highest correlation with human judgement on paraphrase classification meanwhile reamin the computional cost low as it roughtly equal to one token generation cost.
 """