Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910253979795456 |
|---|---|
| author | Jin, Hongbo Zhu, Mingnan Tian, Jingqi Jiang, Xu Du, Zhongjing Tang, Haoran Xie, Siyi Zhang, Qiaoman Ding, Jiayu |
| author_facet | Jin, Hongbo Zhu, Mingnan Tian, Jingqi Jiang, Xu Du, Zhongjing Tang, Haoran Xie, Siyi Zhang, Qiaoman Ding, Jiayu |
| contents | While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamically extract, internalize, and apply new knowledge from complex, task-specific contexts. Recent evaluations on the CL-Bench reveal a critical capability gap: frontier models solve only 17.2% of context-dependent tasks on average. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25354 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis Jin, Hongbo Zhu, Mingnan Tian, Jingqi Jiang, Xu Du, Zhongjing Tang, Haoran Xie, Siyi Zhang, Qiaoman Ding, Jiayu Artificial Intelligence While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamically extract, internalize, and apply new knowledge from complex, task-specific contexts. Recent evaluations on the CL-Bench reveal a critical capability gap: frontier models solve only 17.2% of context-dependent tasks on average. |
| title | Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.25354 |