We lifted 5 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| iaar-shanghai/grimoire | canonical | 5 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| cal_std_dev | Ran | iaar-shanghai/grimoire/analyst.py code served (permissive licence) · get_code("6982375148c368d5") |
| catch_all_exceptions | Ran | iaar-shanghai/grimoire/experiment.py code served (permissive licence) · get_code("d9c9239142204c58") |
| load_yaml_conf | Ran | iaar-shanghai/grimoire/core/load_conf.py code served (permissive licence) · get_code("5fb0226b327b8528") |
| read_all_results | Ran | iaar-shanghai/grimoire/analyst.py code served (permissive licence) · get_code("37d53773023b0c04") |
| read_results | Ran | iaar-shanghai/grimoire/analyst.py code served (permissive licence) · get_code("2d8e7193d8cbfea4") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In-context Learning (ICL) is one of the key methods for enhancing the performance of large language models on specific tasks by providing a set of few-shot examples. However, the ICL capability of different types of models shows significant variation due to factors such as model architecture, volume of learning data, and the size of parameters. Generally, the larger the model's parameter size and the more extensive the learning data, the stronger its ICL capability. In this paper, we propose a method SLEICL that involves learning from examples using strong language models and then summarizing and transferring these learned skills to weak language models for inference and application. This ensures the stability and effectiveness of ICL. Compared to directly enabling weak language models to learn from prompt examples, SLEICL reduces the difficulty of ICL for these models. Our experiments, conducted on up to eight datasets with five language models, demonstrate that weak language models achieve consistent improvement over their own zero-shot or few-shot capabilities using the SLEICL method. Some weak language models even surpass the performance of GPT4-1106-preview (zero-shot) with the aid of SLEICL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2401.03385")
get_code_for_paper("2401.03385")
have("2401.03385")
Connect an agent — have() is free.