AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking
This addresses inefficiencies in retrieval-based applications for users needing cost-effective reranking, though it is incremental as it builds on existing LLM reranking methods.
The paper tackled the inefficiency of fixed-computation listwise reranking with LLMs by proposing AcuRank, an adaptive framework that dynamically adjusts computation based on uncertainty estimates, achieving a superior accuracy-efficiency trade-off on TREC-DL and BEIR benchmarks.
Listwise reranking with large language models (LLMs) enhances top-ranked results in retrieval-based applications. Due to the limit in context size and high inference cost of long context, reranking is typically performed over a fixed size of small subsets, with the final ranking aggregated from these partial results. This fixed computation disregards query difficulty and document distribution, leading to inefficiencies. We propose AcuRank, an adaptive reranking framework that dynamically adjusts both the amount and target of computation based on uncertainty estimates over document relevance. Using a Bayesian TrueSkill model, we iteratively refine relevance estimates until reaching sufficient confidence levels, and our explicit modeling of ranking uncertainty enables principled control over reranking behavior and avoids unnecessary updates to confident predictions. Results on the TREC-DL and BEIR benchmarks show that our method consistently achieves a superior accuracy-efficiency trade-off and scales better with compute than fixed-computation baselines. These results highlight the effectiveness and generalizability of our method across diverse retrieval tasks and LLM-based reranking models.