# AgriJev: Efficient Agricultural Candidate Scoring with Multi-Scale Adapted Models

arXiv: https://arxiv.org/abs/2610.19478 · HTML: https://mlsanity.com/paper/2610.19478/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 22 of 22)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [Revisiting Pre-Trained Models for Chinese Natural Language Processing](https://mlsanity.com/paper/2004.13922/) (2020)
- [Symbol tuning improves in-context learning in language models](https://mlsanity.com/paper/2305.08298/) (2023)
- [Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning](https://mlsanity.com/paper/2306.01150/) (2023)
- [Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors](https://mlsanity.com/paper/2406.01026/) (2024)
- [GLiClass: Generalist Lightweight Model for Sequence Classification Tasks](https://mlsanity.com/paper/2508.07662/) (2025)
- [Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective](https://mlsanity.com/paper/2210.08590/) (2022)
- [ChatAgri: Exploring Potentials of ChatGPT on Cross-linguistic Agricultural Text Classification](https://mlsanity.com/paper/2305.15024/) (2023)
- [An Improved Traditional Chinese Evaluation Suite for Foundation Model](https://mlsanity.com/paper/2403.01858/) (2024)
- [SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science](https://mlsanity.com/paper/2505.13220/) (2025)
- [AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents](https://mlsanity.com/paper/2212.10762/) (2022)
- [BhashaBench V1: A Comprehensive Benchmark for the Quadrant of Indic Domains](https://mlsanity.com/paper/2510.25409/) (2025)
- [Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions](https://mlsanity.com/paper/2509.02452/) (2025)

## Abstract (arXiv)

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.