Metraipolis › archive › dc_8783de080e78
Emo-Jev: Probabilistic Reasoning for Emotion Classification with Jev — arXiv:2610.08829
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08829
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:25:58.834Z
- SHA-256 of the archived text
21f0d3646a7521c6b8fa9f488b4e8347503ada020169c4baa1db3916d02e82fa- Stable URL of this page
https://metraipolis.com/documento/dc_8783de080e78
How to cite
Emo-Jev: Probabilistic Reasoning for Emotion Classification with Jev — arXiv:2610.08829 — arXiv (en), https://arxiv.org/abs/2610.08829 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8783de080e78 (Metraipolis archive dc_8783de080e78, sha256 21f0d3646a7521c6b8fa9f488b4e8347503ada020169c4baa1db3916d02e82fa)
BibTeX
@misc{dc8783de080e78,
title = {Emo-Jev: Probabilistic Reasoning for Emotion Classification with Jev — arXiv:2610.08829},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08829},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8783de080e78; sha256 21f0d3646a7521c6b8fa9f488b4e8347503ada020169c4baa1db3916d02e82fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08829. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Jev offers an alternative interface for language understanding: given an input and predefined questions, it returns probabilistic decisions rather than free-form responses. Whether this interface can support effective reasoning for text classification against leading LLMs remains an open questions. We introduce Emo-Jev, a training-free framework with two complementary implementations. Emo-Jev-D decomposes classification into task-specific atomic judgments and composes their probabilities into a final prediction. Emo-Jev-SC constructs multiple judgment paths from complementary perspectives and aggregates their predictions into a consensus decision. We evaluate Emo-Jev on eight datasets spanning sentiment analysis, emotion recognition, sarcasm detection and humor detection, comparing against direct Jev classification and five SoTA LLMs under input/output and chain-of-thought reasoning. Standard Jev achieves 62.93\% average macro-F1 versus 67.28\% for the strongest LLM baseline, with lower observed latency and generally lower cost. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.08829 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T10:24:06.304Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).