paper-with-me

Papers

Optimally Biased Expertise

2022-09-27 · Pavel Ilinov, Andrei Matveenko, Maxim Senkov, Egor Starkov

This paper shows that the principal can strictly benefit from delegating a decision to an agent whose opinion differs from that of the principal. We consider a "delegated expertise" problem, in which the agent has an advantage in information acquisition relative to the principal, as opposed to having preexisting private information. When the principal is ex ante predisposed towards some action, it is optimal for her to hire an agent who is predisposed towards the same action, but to a smaller extent, since such an agent would acquire more information, which outweighs the bias stemming from misalignment. We show that belief misalignment between an agent and a principal is a viable instrument in delegation, performing on par with contracting and communication in a class of problems.

📄 PDF Abstract BibTeX arXiv:2209.13689

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities

2025-05-17 · Jingxue Chen, Qingkun Tang, Qianchun Lu, Siyuan Fang

Although large language models (LLMs) perform well in general tasks, domain-specific applications suffer from hallucinations and accuracy limitations. Continual Pre-Training (CPT) approaches encounter two key issues: (1)…

Math

Dealing with Expert Bias in Collective Decision-Making

2021-06-25 · Axel Abels, Tom Lenaerts, Vito Trianni, Ann Nowé

Quite some real-world problems can be formulated as decision-making problems wherein one must repeatedly make an appropriate choice from a set of alternatives. Multiple expert judgements, whether human or artificial, can…

Decision Making

How Far Can Fairness Constraints Help Recover From Biased Data?

2023-12-16 · Mohit Sharma, Amit Deshpande

A general belief in fair classification is that fairness constraints incur a trade-off with accuracy, which biased data may worsen. Contrary to this belief, Blum & Stangl (2019) show that fair classification with equal o…

Fairness

Leveraging Crowdsourcing Data For Deep Active Learning - An Application: Learning Intents in Alexa

2018-03-12 · Jie Yang, Thomas Drake, Andreas Damianou, Yoelle Maarek

This paper presents a generic Bayesian framework that enables any deep learning model to actively learn from targeted crowds. Our framework inherits from recent advances in Bayesian deep learning, and extends existing wo…

Active LearningDeep Learningintent-classificationIntent Classification

Learning to Rank Academic Experts in the DBLP Dataset

2015-01-21 · Catarina Moreira, Bruno Martins, Pável Calado

Expert finding is an information retrieval task that is concerned with the search for the most knowledgeable people with respect to a specific topic, and the search is based on documents that describe people's activities…

Information RetrievalLearning-To-RankRetrieval