OptiSeq: Ordering Examples On-The-Fly for In-Context Learning
This addresses a practical issue for developers using LLMs in applications, offering a dataset-free solution to enhance performance, though it is incremental as it builds on prior work on ICL improvements.
The paper tackles the problem of in-context learning fragility in LLMs by showing that example order affects performance, and introduces OptiSeq, an inference-time optimization method that improves accuracy by 5.5-10.5 percentage points across tasks.
Developers using LLMs and LLM-based agents in their applications have provided plenty of anecdotal evidence that in-context-learning (ICL) is fragile. In this paper, we show that in addition to the quantity and quality of examples, the order in which the in-context examples are listed in the prompt affects the output of the LLM and, consequently, their performance. While prior work has explored improving ICL through dataset-dependent techniques, we introduce OptiSeq, a purely inference-time, dataset-free optimization method that efficiently determines the best example order. OptiSeq leverages log probabilities of LLM-generated outputs to systematically prune the search space of possible orderings and recommend the best order(s) by distinguishing orderings that yield high levels of accuracy and those that underperform. Extensive empirical evaluation on multiple LLMs, datasets, and prompts demonstrate that OptiSeq improves accuracy by 5.5 - 10.5 percentage points across multiple tasks.