arXiv cs.CL· Xuechen Li (University of Minnesota Twin Cities)·· 3 天前AI 评分18
AgriJev：基于多尺度适配模型的高效农业候选评分
AgriJev: Efficient Agricultural Candidate Scoring with Multi-Scale Adapted Models
AI 导读
研究团队推出 AgriJev，基于 Qwen3.5 适配的 0.8B、2B、4B、9B 系列模型，通过单次前向调用对农业文本、判断问题和候选定义返回评分与相对概率。
正文 · 原文
Authors:Xuechen Li (University of Minnesota Twin Cities)
Abstract:Agricultural systems make decisions over heterogeneous entity types, textual judgments, and knowledge-question options. Generating a textual answer adds decoding and extraction steps to decisions that ultimately require a candidate choice. We introduce AgriJev, a family of adapted Qwen3.5 models at 0.8B, 2B, 4B, and 9B. A shared interface conditions on agricultural text, a judgment question, and candidate definitions, returning scores and relative probabilities in one forward call. We prepare source-aware training records and frozen evaluations from existing agricultural resources, retaining original groups and annotation provenance. Comparisons include original Qwen3.5 models and matched agricultural SFT models, both evaluated through native answer generation. Across 17 external test views, AgriJev-9B reaches 75.44% mean accuracy, exceeding the original and SFT generators by 5.89 and 3.79 percentage points. It outperforms the original generator on 13 views and narrows the mean gap to hosted Jev 1.13.0. On a fixed A100 workload, its median scoring latency is approximately half that of same-scale answer generation. Task-dependent gains and failures characterize a practical choice among agricultural model weights and inference contracts.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.19478 [cs.CL] |
| (or arXiv:2610.19478v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19478 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xuechen Li [view email]
[v1]
Wed, 14 Oct 2026 02:56:17 UTC (191 KB)
来源：arXiv cs.CL · arxiv.org