DBES supplies a multi-domain benchmark and five metrics (Routing Specialization, Normalized Effective Rank, Domain Isolation, Routing Stiffness Score, N-gram Expertise) that reveal distinct specialization patterns across MoE models and enable 66-94% domain gains with 15% training resources.
Modular deep learning
5 Pith papers cite this work, alongside 12 external citations. Polarity classification is still indexing.
5
Pith papers citing it
12
external citations · external index
verdicts
UNVERDICTED 5representative citing papers
MoRe identifies modular structure in representations themselves to enable principled reuse, alignment, and expansion of modules during continual adaptation on sequential data.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
Red-Bandit adapts online to LLM failure modes by dynamically selecting among RL-trained LoRA attack-style experts via a bandit policy, reporting SOTA ASR@10 on AdvBench with lower-perplexity prompts.
AI's compositional reasoning failures originate in psychological learning paradigms that shaped its architectures, and the ReSynth trimodular framework is proposed to embed systematicity structurally.
citing papers explorer
-
DBES: A Systematic Benchmark and Metric Suite for Evaluating Expert Specialization in Large-Scale MoEs
DBES supplies a multi-domain benchmark and five metrics (Routing Specialization, Normalized Effective Rank, Domain Isolation, Routing Stiffness Score, N-gram Expertise) that reveal distinct specialization patterns across MoE models and enable 66-94% domain gains with 15% training resources.
-
MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
MoRe identifies modular structure in representations themselves to enable principled reuse, alignment, and expansion of modules during continual adaptation on sequential data.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts
Red-Bandit adapts online to LLM failure modes by dynamically selecting among RL-trained LoRA attack-style experts via a bandit policy, reporting SOTA ASR@10 on AdvBench with lower-perplexity prompts.
-
How Psychological Learning Paradigms Shaped and Constrained Artificial Intelligence
AI's compositional reasoning failures originate in psychological learning paradigms that shaped its architectures, and the ReSynth trimodular framework is proposed to embed systematicity structurally.