Emo-Jev: Probabilistic Reasoning for Emotion Classification with Jev
Quick Answer
Emo-Jev introduces a training-free framework for emotion classification, outperforming standard Jev with an average macro-F1 of 67.28% against 62.93% for Jev.
Quick Take
It utilizes two implementations, Emo-Jev-D and Emo-Jev-SC, to enhance decision-making efficiency while maintaining lower latency and costs compared to leading .
Key Points
- Emo-Jev-D decomposes classification into atomic judgments for final predictions.
- Emo-Jev-SC aggregates predictions from multiple judgment paths for consensus.
- Evaluated on eight datasets including sentiment analysis and humor detection.
- Standard Jev shows lower performance than the best LLM baseline.
- Emo-Jev maintains lower latency and costs compared to leading models.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.08829 [cs.CL] |
| (or arXiv:2610.08829v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08829 arXiv-issued DOI via DataCite |
Submission history
From: Yazhou Zhang [view email]
[v1]
Sun, 27 Sep 2026 01:35:32 UTC (2,852 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.