Evaluating the Abilities of LLMs and SpeechLMs in Discovering Implicit Contents of Italian Political Speeches

Lorenzo Gregori, Walter Paci, Alessandro Panunzi


Abstract
This research investigates the pragmatic competence of Large Language Models (LLMs) in interpreting implicit meanings within Italian political discourse. Using the IMPAQTS-PIDMM dataset, which is a multimodal benchmark derived from the 2.5-million-token IMPAQTS corpus, the experiment evaluates how effectively models identify tendentious content such as presuppositions and implicatures. The study compares the performance of text-only LLMs against speech-based models (SpeechLMs) that process both audio and transcriptions to determine if acoustic cues enhance understanding. The results reveal that text-only models significantly outperform multimodal variants, with Qwen2.5-72B achieving the highest global accuracy of 0.863. Surprisingly, the inclusion of audio did not improve performance, as SpeechLMs like GPT-4o-mini-audio-preview and Qwen2-Audio-7B-Instruct obtained lower accuracy scores and a higher frequency of missed answers compared to their text-only equivalents. Across all tested architectures, models generally demonstrated a superior ability to process presuppositions over implicatures.
Anthology ID:
2026.politicalnlp-1.18
Volume:
Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Haithem Afli, Houda Bouamor, Wajdi Zaghouani, Sahar Ghannay, Shehenaz Hossain
Venues:
PoliticalNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
165–170
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-politicalnlp-18
DOI:
10.63317/4y7ki8iw4mwe
Bibkey:
Cite (ACL):
Lorenzo Gregori, Walter Paci, and Alessandro Panunzi. 2026. Evaluating the Abilities of LLMs and SpeechLMs in Discovering Implicit Contents of Italian Political Speeches. In Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026), pages 165–170, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Evaluating the Abilities of LLMs and SpeechLMs in Discovering Implicit Contents of Italian Political Speeches (Gregori et al., PoliticalNLP 2026)
Copy Citation: