paper-with-me

홈 › Papers

On Monotonic Aggregation for Open-domain QA

2023-08-08 · Sang-eun Han, Yeonseok Jeong, Seung-won Hwang, Kyungjae Lee

Question answering (QA) is a critical task for speech-based retrieval from knowledge sources, by sifting only the answers without requiring to read supporting documents. Specifically, open-domain QA aims to answer user questions on unrestricted knowledge sources. Ideally, adding a source should not decrease the accuracy, but we find this property (denoted as "monotonicity") does not hold for current state-of-the-art methods. We identify the cause, and based on that we propose Judge-Specialist framework. Our framework consists of (1) specialist retrievers/readers to cover individual sources, and (2) judge, a dedicated language model to select the final answer. Our experiments show that our framework not only ensures monotonicity, but also outperforms state-of-the-art multi-source QA methods on Natural Questions. Additionally, we show that our models robustly preserve the monotonicity against noise from speech recognition. We publicly release our code and setting.

📄 PDF Abstract BibTeX arXiv:2308.04176

Code (1)

yeonseokjeong/judge-specialist 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingNatural QuestionsQuestion AnsweringRetrievalspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Dangerous Liaisons of Convex Learning and Non-Affine Aggregation

2026-06-26 · Thomas Boudou, Batiste Le Bars, Nirupam Gupta, Aurélien Bellet arxiv

Last-iterate convergence and generalization guarantees in first-order convex learning hinge on the monotonicity of the update operator. While linear averaging preserves the monotonicity of gradient updates, this property…

Weak comonotonicity

2019-09-11

The classical notion of comonotonicity has played a pivotal role when solving diverse problems in economics, finance, and insurance. In various practical problems, however, this notion of extreme positive dependence stru…

Weakly monotone averaging functions

2014-08-02 · Tim Wilkin, Gleb Beliakov

Monotonicity with respect to all arguments is fundamental to the definition of aggregation functions. It is also a limiting property that results in many important non-monotonic averaging functions being excluded from th…

Multi-Teacher Ensemble Distillation: A Mathematical Framework for Probability-Domain Knowledge Aggregation

2026-01-14 · Aaron R. Flouro, Shawn P. Chadwick arxiv

Building on the probability-domain distillation framework of Sparse-KD, we develop an axiomatic, operator-theoretic framework for multi-teacher ensemble knowledge distillation. Rather than prescribing a specific aggregat…

Knowledge Distillation

On the Correspondence Between Monotonic Max-Sum GNNs and Datalog

2023-05-29 · David Tena Cucala, Bernardo Cuenca Grau, Boris Motik, Egor V. Kostylev

Although there has been significant interest in applying machine learning techniques to structured data, the expressivity (i.e., a description of what can be learned) of such techniques is still poorly understood. In thi…