AI Paper Atlas

Research map / Large language models / Alignment and preferences

Align³GR: Unified Multi-Level Alignment for LLM-based Generative Recommendation

Wencai Ye, Mingjie Sun, Shuhang Chen, Wenjin Wu, Peng Jiang

AAAI 2026 · Large language models › Alignment and preferences · approach: Robust and calibrated DPO · 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
use dual user-item tokenization instead of item-only (ablation)Align3GR · InstrumentsRecall@10: 0.1322 -> 0.1390Improved
add collaborative features to item tokenization (ablation)Align3GR · InstrumentsRecall@10: 0.1322 -> 0.1346Improved
add user-item alignment (U2I loss) to dual tokenization (ablation)Align3GR · InstrumentsRecall@10: 0.1390 -> 0.1426Improved
add C1-C3 implicit alignment tasks to SEQ (ablation)Align3GR · InstrumentsRecall@10: 0.1329 -> 0.1344No clear effect
add item alignment task B1 (ablation)Align3GR · InstrumentsRecall@10: 0.1344 -> 0.1399Improved
inject user SCID into prompts (ablation)Align3GR · InstrumentsRecall@10: 0.1399 -> 0.1417Improved
add bidirectional user alignment B2 (ablation)Align3GR · InstrumentsRecall@10: 0.1417 -> 0.1442Improved
add self-play to Softmax-DPO (ablation)Align3GR · InstrumentsRecall@10: 0.1295 -> 0.1356Improved
add progressive easy-to-hard training to SP-DPO (ablation)Align3GR · InstrumentsRecall@10: 0.1356 -> 0.1396Improved
add progressive training to RF-DPO (ablation)Align3GR · InstrumentsRecall@10: 0.1414 -> 0.1442Improved
add real-world feedback DPO after progressive SP-DPO (ablation)Align3GR · InstrumentsRecall@10: 0.1396 -> 0.1442Improved
deploy Align3GR instead of TIGER onlineTIGER · Industrial ad platformRecall@100 / revenue: 0.229 -> 0.242 Recall@100; revenue +0.555% -> +1.432%Improved

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