Model Card for AU-clarification_gemma-2-9b-it
Gemma-2-9b-it finetuned on the GDN-CC dataset for the task of Argumentative Unit Clarification. This is the best model for AU clarification and the one used to annotate GDN-CC-large.
Uses
It is recommended to use it with the vLLM framework:
from vllm import LLM, SamplingParams
llm = LLM(model="LequeuISIR/AU-clarification_gemma-2-9b-it",
max_model_len=2048)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
sampling_params = SamplingParams(temperature=0.2, max_tokens=2000)
messages = [
{"role": "user", "content": f"{PROMPT}texte initial:\n {item["opinionText"].strip()}\n\n segment à clarifier:\n{item["AU"].strip()}"}
]
prompt_string = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
outputs = llm.generate([prompt_string], sampling_params)
with the prompt being:
PROMPT= """
Je vais te donner un segment de texte d'opinions en français, ainsi que le texte initial dont il est tiré. Ton travail est de réécrire ce segment \
d'opinion de manière claire. En particulier, tu dois d'abord corriger les fautes d'orthographe, de grammaire, et de syntaxe. Tu dois aussi ajouter \
le contexte présent dans le texte initial si il est important pour la compréhension du segment. Le texte final clarifié doit être compréhensible \
sans accès ni au texte initial ni a son sous-segment. Si le segment est déjà clair et bien écrit, tu dois simplement le recopier. \
Tu dois ressortir UNIQUEMENT la clarification du segment et rien d'autre. \n\n
"""
BibTeX:
@inproceedings{lequeu-etal-2026-gdn,
title = "The {GDN}-{CC} Dataset: Automatic Corpus Clarification for {AI}-enhanced Democratic Citizen Consultations",
author = {Lequeu, Pierre-Antoine and
Labat, L{\'e}o and
Cave, Laur{\`e}ne and
Lejeune, Ga{\"e}l and
Yvon, Fran{\c{c}}ois and
Piwowarski, Benjamin},
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1523/",
doi = "10.18653/v1/2026.acl-long.1523",
pages = "32976--33006",
ISBN = "979-8-89176-390-6",
abstract = "LLMs are ubiquitous in modern NLP, and while their applicability extends to texts produced for democratic activities such as online deliberations or large-scale citizen consultations, ethical questions have been raised for their usage as analysis tools. We continue this line of research with two main goals: (a) to develop resources that can help standardize citizen contributions in public forums at the \textbf{pragmatic level}, and make them easier to use in topic modeling and political analysis; (b) to study how well this standardization can reliably be performed by small, open-weights LLMs, \textit{i.e.} models that can be run locally and transparently with limited resources. Accordingly, we introduce \textbf{Corpus Clarification} as a preprocessing framework for large-scale consultation data that transforms noisy, multi-topic contributions into structured, self-contained argumentative units ready for downstream analysis. We present \textbf{GDN-CC}, a manually-curated dataset of 1,231 contributions to the French \textit{Grand D{\'e}bat National}, comprising 2,285 argumentative units annotated for argumentative structure and manually clarified. We then show that finetuned Small Language Models match or outperform LLMs on reproducing these annotations, and measure their usability for an opinion clustering task. We finally release \textbf{GDN-CC-large}, an automatically annotated corpus of 240k contributions, the largest annotated democratic consultation dataset to date."
}