AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Inductive Generative Recommendation via Retrieval-based Speculation

Yijie Ding, Jiacheng Li, Julian McAuley, Yupeng Hou

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 18 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
add inductive drafting to SpecGR++ (ablation)SpecGR++ · Amazon GamesRecall@50: 0.0609 -> 0.0717Improved
add likelihood score adjustment (exclude item identification token) (ablation)SpecGR++ · Amazon GamesRecall@50: 0.0712 -> 0.0717Improved
add guided re-drafting (ablation)SpecGR++ · Amazon GamesRecall@50: 0.0611 -> 0.0717Improved
add verification-based re-ranking (ablation)SpecGR++ · Amazon GamesRecall@50: 0.0703 -> 0.0717Improved
add adaptive exiting (ablation)SpecGR++ · Amazon OfficeRecall@10: 0.0203 -> 0.0250Improved
use dedicated contrastive pretraining for the GR encoder instead of raw TIGER encoder states (ablation)SpecGR++ · Amazon GamesRecall@50: 0.0581 -> 0.0717Improved
add learning-to-rank fine-tuning after contrastive pretraining (ablation)SpecGR++ · Amazon GamesRecall@50: 0.0692 -> 0.0717Improved
add SpecGR drafting and verification to a TIGER backboneTIGER · Amazon Games unseen subsetRecall@50: TIGER fails on unseen (-) -> 0.0312Improved
increase draft size (ablation)SpecGR++ · Amazon GamesUnseen and in-sample Recall@50Mixed
increase beam size (ablation)SpecGR++ · Amazon GamesUnseen and in-sample Recall@50Mixed
lower acceptance threshold (ablation)SpecGR++ · Amazon GamesIn-sample Recall@50Hurt
plug SpecGR into DSI backbone with different draftersDSI · Amazon GamesNDCG@50 overall: 0.0198 -> 0.0220Improved

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