AI ethics evidence index Search
Source-linked daily record
Evidence record 4607 · automatically gathered

EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent

Gradient-based preference optimization methods for large language model (LLM) alignment suffer from preference collapse, converging to narrow behavioral modes while neglecting preference diversity. We introduce EvoPref, a multi-objective evolutionary algorithm that maintains populations of Low-Rank Adaptation (LoRA) adapters optimized across helpfulness, harmlessness, and honesty objectives using Non-dominated Sorting Genetic Algorithm II (NSGA-II) selection with archive-based diversity preserva

Record details

Published: 10 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Same publisher byline · Shared topic: Safety & alignment

Brain-LLM Alignment Tracks Training Data, Not Typology

arXiv · 21 May 2026

Same publisher byline · Shared topic: Safety & alignment

Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography

arXiv · 21 May 2026

Same publisher byline · Shared topic: Safety & alignment

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models

arXiv · 20 April 2026

Same publisher byline

SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters

arXiv · 1 May 2026

Shared topic: Safety & alignment

Flag Varieties: A Geometric Framework for Deep Network Alignment

arXiv · 11 May 2026

Shared topic: Safety & alignment

Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions

arXiv · 11 May 2026

How to cite this record

ethics.ai (10 May 2026), “EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent,” evidence record 4607, https://ethics.ai/record/4607 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.