# OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training

arXiv: https://arxiv.org/abs/2606.25906 · HTML: https://mlsanity.com/paper/2606.25906/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Improve Vision Language Model Chain-of-thought Reasoning](https://mlsanity.com/paper/2410.16198/) (2024)
- [OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles](https://mlsanity.com/paper/2503.17352/) (2025)
- [Perception-R1: Pioneering Perception Policy with Reinforcement Learning](https://mlsanity.com/paper/2504.07954/) (2025)
- [SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL](https://mlsanity.com/paper/2504.11455/) (2025)
- [NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation](https://mlsanity.com/paper/2504.13055/) (2025)
- [A Survey on Post-training of Large Language Models](https://mlsanity.com/paper/2503.06072/) (2025)
- [Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning](https://mlsanity.com/paper/2504.16656/) (2025)
- [Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.16188/) (2025)
- [VisRL: Intention-Driven Visual Perception via Reinforced Reasoning](https://mlsanity.com/paper/2503.07523/) (2025)
- [OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?](https://mlsanity.com/paper/2412.01175/) (2024)
- [Deciphering Oracle Bone Language with Diffusion Models](https://mlsanity.com/paper/2406.00684/) (2024)
- [Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning](https://mlsanity.com/paper/2404.12966/) (2024)
- [An open dataset for the evolution of oracle bone characters: EVOBC](https://mlsanity.com/paper/2401.12467/) (2024)
- [Compile Scene Graphs with Reinforcement Learning](https://mlsanity.com/paper/2504.13617/) (2025)
- [OracleSage: Towards Unified Visual-Linguistic Understanding of Oracle Bone Scripts through Cross-Modal Knowledge Fusion](https://mlsanity.com/paper/2411.17837/) (2024)
- [Puzzle Pieces Picker: Deciphering Ancient Chinese Characters with Radical Reconstruction](https://mlsanity.com/paper/2406.03019/) (2024)
- [FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings](https://mlsanity.com/paper/2501.06645/) (2025)
- [AdaMHF: Adaptive Multimodal Hierarchical Fusion for Survival Prediction](https://mlsanity.com/paper/2503.21124/) (2025)
- [Interpretable Oracle Bone Script Decipherment through Radical and Pictographic Analysis with LVLMs](https://mlsanity.com/paper/2508.10113/) (2025)
- [A Cross-Font Image Retrieval Network for Recognizing Undeciphered Oracle Bone Inscriptions](https://mlsanity.com/paper/2409.06381/) (2024)

## Abstract (arXiv)

With the advancement of artificial intelligence, research on oracle bone scripts has entered a new era. However, existing methods and benchmarks remain largely confined to recognition tasks, overlooking the equally crucial aspect of oracle bone analysis. To address this gap, we propose OracleAnalyser, a reasoning framework for oracle bone analysis based on post-training techniques. Specifically, we fine-tune Qwen2.5-VL-3B-Instruct through multiple post-training stages and introduce a new preference optimization algorithm, Stable Focal Preference Optimization (SFPO), tailored to the characteristics of oracle bone datasets. In addition, we release both an oracle bone reasoning dataset and an oracle bone preference dataset, and further construct a new benchmark to evaluate models' analytical capabilities for oracle bone scripts. Extensive experiments validate the superior analytical performance of OracleAnalyser, which achieves remarkable results with only 3B parameters, surpassing models with substantially larger scales.