arXiv：cs.CL· Yazhou Zhang, Junhao Yu·· 3 小时前AI 评分24
Emo-Jev：用 Jev 概率推理做情感分类，无需训练即可媲美 SoTA LLM
Emo-Jev: Probabilistic Reasoning for Emotion Classification with Jev
AI 导读
Emo-Jev 是一个免训练框架，通过 Jev 的概率决策接口做文本分类，含分解原子判断的 Emo-Jev-D 与多路径共识的 Emo-Jev-SC 两种实现。在覆盖情感分析、情绪识别、讽刺与幽默检测的八个数据集上，标准 Jev 平均 macro-F1 为 62.93%，最强 LLM 基线为 67.28%，但 Jev 延迟更低、成本总体更省。
正文
Abstract: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)
来源：arXiv：cs.CL · arxiv.org