Research map / Large language models / Language, safety and interpretability
InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling
Xiaolei Diao, Zhihan Zhou, Lida Shi, Ting Wang, Ruihua Qi, Daqian Shi, Hao Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use InteChar character list instead of original list | Qwen-7B-Chat · Oracle cloze (OracleCS) | NDCG@10: 0.302 -> 0.842 | Improved |
| use InteChar character list instead of original list | GPT-2 · Oracle cloze (OracleCS) | MRR@10: 0.168 -> 0.534 | Improved |
| use InteChar character list instead of original list | BERT · Oracle cloze (OracleCS) | MRR@10: 0.134 -> 0.375 | Improved |
| use InteChar character list instead of original list | GLM-4-9B · Commentary-to-Text Retrieval | MRR@500: 0.176 -> 0.285 | Improved |
| use InteChar character list instead of original list | Qwen-7B-Chat · Commentary-to-Text Retrieval | NDCG@500: 0.418 -> 0.579 | Improved |
| use InteChar character list instead of original list | Qwen-7B-Chat · OracleCS fine-tuning (LoRA) average | accuracy (%): 92.32 -> 93.06 | Improved |
| use InteChar character list instead of original list | Llama-3-8B · OracleCS fine-tuning (LoRA) Translation | accuracy (%): 83.52 -> 83.43 | No clear effect |
| use InteChar character list instead of original list | TongGu-LLM · OracleCS fine-tuning (LoRA) average | accuracy (%): 92.21 -> 92.92 | Improved |
| use InteChar character list instead of original list | Llama-3-8B · OracleCS fine-tuning (LoRA) average | accuracy (%): 81.41 -> 81.61 | No clear effect |
Closest papers by meaning
- OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones? (ICLR 2025 · similarity 0.87)
- Component-Level Segmentation for Oracle Bone Inscription Decipherment (AAAI 2025 · similarity 0.86)
- Towards Automated Chinese Ancient Character Restoration: A Diffusion-Based Method with a New Dataset (AAAI 2024 · similarity 0.86)
- WenMind: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Classical Literature and Language Arts (NeurIPS 2024 · similarity 0.85)
- Reading between the Lines: Image-Based Order Detection in OCR for Chinese Historical Documents (AAAI 2024 · similarity 0.83)
- Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
