Rough-set analysis finds 16.4% of 305 concept profiles in Derm7pt inconsistent (306 images), capping hard CBM accuracy at 92.1%; symmetric filtering produces a 705-image consistent benchmark where EfficientNet-B5 reaches 0.90 label accuracy.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
Case study of 18,020 Kubernetes PRs shows label-diff congruence is prevalent and stable, with higher congruence linked to fewer review participants among core developers and more among one-time contributors.
Generative LMs in laissez-faire open-ended prompting settings disproportionately generate subordinated portrayals of minoritized race, gender, and sexual orientation identities at rates hundreds to thousands of times higher than empowering ones.
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
Framework and software implementation for data-driven trigger efficiency estimation at LHCb using reconstructed candidate properties.
citing papers explorer
-
Concept Inconsistency in Dermoscopic Concept Bottleneck Models: A Rough-Set Analysis of the Derm7pt Dataset
Rough-set analysis finds 16.4% of 305 concept profiles in Derm7pt inconsistent (306 images), capping hard CBM accuracy at 92.1%; symmetric filtering produces a 705-image consistent benchmark where EfficientNet-B5 reaches 0.90 label accuracy.
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
Efficiency for Experts, Visibility for Newcomers: A Case Study of Label-Code Alignment in Kubernetes
Case study of 18,020 Kubernetes PRs shows label-diff congruence is prevalent and stable, with higher congruence linked to fewer review participants among core developers and more among one-time contributors.
-
Laissez-Faire Harms: Algorithmic Biases in Generative Language Models
Generative LMs in laissez-faire open-ended prompting settings disproportionately generate subordinated portrayals of minoritized race, gender, and sexual orientation identities at rates hundreds to thousands of times higher than empowering ones.
-
PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
-
A framework and implementation for data-driven trigger efficiency estimation at LHCb
Framework and software implementation for data-driven trigger efficiency estimation at LHCb using reconstructed candidate properties.