AI Paper Atlas

Research map / Large language models / Alignment and preferences

NextQuill: Causal Preference Modeling for Enhancing LLM Personalization

Xiaoyan Zhao, Juntao You, Yang Zhang, Wenjie Wang, Hong Cheng, Fuli Feng, See-Kiong Ng, Tat-Seng Chua

ICLR 2026 · Large language models › Alignment and preferences · approach: LLM-as-judge and feedback data

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 causal preference alignment (NextQuill)ContextSFT · Book ReviewROUGE-1: 0.1661 -> 0.2318Improved
add MCE-only loss (ablation)SFT · Book ReviewROUGE-1: 0.0752 -> 0.1827Improved
add DCE token weighting only (ablation)SFT · Book ReviewROUGE-1: 0.0752 -> 0.1958Improved
combine MCE-DCE alignment and token weighting (ablation)DCE only · Book ReviewROUGE-1: 0.1958 -> 0.2318Improved
replace preference-driven tokens with random tokens (ablation)NextQuill · Book ReviewROUGE-1: 0.2308 -> 0.1811Hurt
scale backbone from 3B to 7BNextQuill · Book ReviewROUGE-1: 0.2318 -> 0.4116Improved
add NextQuill on Topic WritingOPPU · Topic WritingBERTScore: 0.7990 vs 0.7957No clear effect
plain SFT without historyQwen base · Topic WritingROUGE-1: 0.0684 -> 0.0345Hurt
stratify by item popularity (ablation)NextQuill vs ContextSFT · Book Review low-popROUGE-1: 0.1651 -> 0.2079Improved
set alpha to 0.05 (ablation)NextQuill · CD Reviewmultiple metricsImproved

Later papers that compared with this method

1 later accepted paper reports NextQuill as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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