Rank It, Then Ask It: Input Reranking for Maximizing the Performance of LLMs on Symmetric Tasks

TL;DR

This paper introduces input reranking techniques for large language models to improve accuracy on symmetric tasks involving unordered input sets, demonstrating significant performance gains through optimized input ordering.

Contribution

The paper proposes a novel input reranking method that leverages a helper LLM to optimize input orderings, significantly enhancing LLM performance on symmetric tasks.

Findings

Reranking improves LLM accuracy by up to 99%.

The approach effectively estimates element relevance and position importance.

Experiments on synthetic and real datasets validate the method's effectiveness.

Abstract

Large language models (LLMs) have quickly emerged as practical and versatile tools that provide new solutions for a wide range of domains. In this paper, we consider the application of LLMs on symmetric tasks where a query is asked on an (unordered) bag of elements. Examples of such tasks include answering aggregate queries on a database table. In general, when the bag contains a large number of elements, LLMs tend to overlook some elements, leading to challenges in generating accurate responses to the query. LLMs receive their inputs as ordered sequences. However, in this problem, we leverage the fact that the symmetric input is not ordered, and reordering should not affect the LLM's response. Observing that LLMs are less likely to miss elements at certain positions of the input, we introduce the problem of LLM input reranking: to find a ranking of the input that maximizes the LLM's accuracy for the given query without making explicit assumptions about the query. Finding the optimal ranking requires identifying (i) the relevance of each input element for answering the query and (ii) the importance of each rank position for the LLM's attention. We develop algorithms for estimating these values efficiently utilizing a helper LLM. We conduct comprehensive experiments on different synthetic and real datasets to validate our proposal and to evaluate the effectiveness of our proposed algorithms. Our experiments confirm that our reranking approach improves the accuracy of the LLMs on symmetric tasks by up to $99\%$ proximity to the optimum upper bound.