AI Paper Atlas

Research map / Large language models / Alignment and preferences

ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models Using Pareto High-Quality Data

Haoran Gu, Handing Wang, Yi Mei, Mengjie Zhang, Yaochu Jin

AAAI 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
represent preferences as directions with Pareto high-quality data instead of linear scalarizationParetoHqD · Helpful Assistant (HH-RLHF, 2 rewards)hypervolume: 0.6325 (RiC) -> 0.7526Improved
use ParetoHqD instead of linear-scalarization baselinesmultiobjective alignment · Helpful Assistant (HH-RLHF, 2 rewards)collapse rate (%): 41.88 (RiC) -> 7.03Improved
small Pareto high-quality training sets and data augmentation from only M+1 modelsParetoHqD · Helpful Assistant (HH-RLHF, 2 rewards)training GPU hours: 132.47 (RiC) -> 55.87Improved
add stage 2 data augmentation and further fine-tuning (ablation)ParetoHqD · Helpful Assistant (HH-RLHF, 2 rewards)Pareto front qualityImproved
replace linear scalarization selection with Pareto filtering and preference directions in SFT data selection (ablation)ParetoHqD stage 1 · Helpful Assistant (HH-RLHF), concave-front sub-datasetPareto front coverageImproved
replace linear scalarization with preference directions in stage 1 data selection (ablation)ParetoHqD stage 1 · Helpful Assistant (HH-RLHF)collapse rate (%): 6.74 -> 6.11No clear effect
train on a small high-quality top-k set instead of the whole scalarized dataset (ablation)SFT · Helpful Assistant (HH-RLHF)collapse rate (%): 35.74 -> 6.74Improved
scalarized SFT on the full set versus the base model (ablation)Llama-2 7B · Helpful Assistant (HH-RLHF)collapse rate (%): 18.63 -> 35.74Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy