# Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees

Source: [Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees](<https://www.sota2.com/research/paper/68fa77001e209131cea70646>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-05T05:00:04.417Z

Authors: Yannis Montreuil, Shu Heng Yeo, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi

Published: 2024-10-21T08:21:00.000Z

## Abstract

Large Language Models excel in generative tasks but exhibit inefficiencies in structured text selection, particularly in extractive question answering. This challenge is magnified in resource-constrained environments, where deploying multiple specialized models for different tasks is impractical. We propose a Learning-to-Defer framework that allocates queries to specialized experts, ensuring high-confidence predictions while optimizing computational efficiency. Our approach integrates a principled allocation strategy with theoretical guarantees on optimal deferral that balances performance and cost. Empirical evaluations on SQuADv1, SQuADv2, and TriviaQA demonstrate that our method enhances answer reliability while significantly reducing computational overhead, making it well-suited for scalable and efficient EQA deployment.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.15761>)

[PDF](<https://arxiv.org/pdf/2410.15761.pdf>)
