paper-with-me

Papers

Logarithmic Scores, Power-Law Discoveries: Disentangling Measurement from Coverage in Agent-Based Evaluation

2026-04-01 · HyunJoon Jung, William Na arxiv

LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their assessments, and if so, how many are needed? Through 960 sessions with two model pairs across 15 tasks, we show that persona-based agent judges produce evaluations indistinguishable from human raters in a Turing-style validation. We then identify a score-coverage dissociation: quality scores improve logarithmically with panel size, while unique issue discoveries follow a sublinear power law-both exhibit diminishing returns, but scores saturate roughly twice as fast as discoveries. We hypothesize this reflects a power law distribution of the finding space: critical issues are discovered first by small panels, while corner cases require progressively larger panels, analogous to species accumulation curves in ecology. The mechanism traces to ensemble diversity-Big Five personality conditioning makes agents probe different quality dimensions, with expert judges acting as adversarial probes that push discovery into the tail of the finding distribution. A controlled ablation confirms that structured persona conditioning, not simple prompting, is required to produce these scaling properties.

📄 PDF Abstract BibTeX arXiv:2604.00477

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Communication-Efficient False Discovery Rate Control via Knockoff Aggregation

2015-06-17 · Weijie Su, Junyang Qian, Linxi Liu

The false discovery rate (FDR)---the expected fraction of spurious discoveries among all the discoveries---provides a popular statistical assessment of the reproducibility of scientific studies in various disciplines. In…

PLOT-CT: Pre-log Voronoi Decomposition Assisted Generation for Low-dose CT Reconstruction

2026-02-12 · Bin Huang, Xun Yu, Yikun Zhang, Yi Zhang 외 arxiv

Low-dose computed tomography (LDCT) reconstruction is fundamentally challenged by severe noise and compromised data fidelity under reduced radiation exposure. Most existing methods operate either in the image or post-log…

Quantum RNNs and LSTMs Through Entangling and Disentangling Power of Unitary Transformations

2025-05-10 · Ammar Daskin

In this paper, we discuss how quantum recurrent neural networks (RNNs) and their enhanced version, long short-term memory (LSTM) networks, can be modeled using the core ideas presented in Ref.[1], where the entangling an…

Disentangling Alzheimer's disease neurodegeneration from typical brain aging using machine learning

2021-09-08 · Gyujoon Hwang, Ahmed Abdulkadir, Guray Erus, Mohamad Habes 외

Neuroimaging biomarkers that distinguish between typical brain aging and Alzheimer's disease (AD) are valuable for determining how much each contributes to cognitive decline. Machine learning models can derive multi-vari…

BIG-bench Machine Learning

Study of filtered-x logarithmic recursive least $p$-power algorithm

2022-01-20 · Z. Zheng, L. Lu, Y. Yu, R. C. de Lamare 외

For active impulsive noise control, a filtered-x recursive least $p$-power (FxRLP) algorithm is proposed by minimizing the weighted summation of the $p$-power of the \emph{a posteriori} errors. Since the characteristic o…