Amit Deshpande, Amit Sharma, Satvik Golechha, Pragya Srivastava
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent work shows that in-context learning and optimization of in-context examples (ICE) can significantly improve the accuracy of large language models (LLMs) on a wide range of tasks, leading to an apparent consensus that ICE optimization is crucial for better performance. However, most of these studies assume a fixed or no instruction provided in the prompt. We challenge this consensus by investigating the necessity of optimizing ICE when task-specific instructions are provided and find that there are many tasks for which it yields diminishing returns. In particular, using a diverse set of tasks and a systematically created instruction set with gradually added details, we find that as the prompt instruction becomes more detailed, the returns on ICE optimization diminish. To characterize this behavior, we introduce a taskspecific metric called Normalized Invariability to Choice of Examples (NICE) that quantifies the learnability of tasks from a given instruction, and provides a heuristic to help decide whether to optimize instructions or ICE for a new task. Given a task, the proposed metric can reliably predict the utility of optimizing ICE compared to using random ICE. Our code is available at https://github.com/microsoft/niceicl.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.06733")
get_code_for_paper("2402.06733")
have("2402.06733")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.06733.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.06733)
Connect an agent — have() is free.