What Makes an Ideal Quote? Recommending “Unexpected yet Rational” Quotations via Novelty

ACL ARR 2026 January Submission215 Authors

Keywords: Quotation Recommendation, Token-level Novelty Estimation, Retrieval-Augmented Generation (RAG), Reranking

Abstract:

Quotation recommendation enriches writing by suggesting quotations that fit a given context, but prior systems largely focus on topical relevance and overlook what makes quotes memorable.
Based on a user study, we find that preferred quotations are often unexpected yet rational, motivating the goal of selecting quotes that are contextually novel while semantically coherent.
We propose NovelQR, which (1) uses a generative label agent to map quotations and contexts into multi-dimensional deep-meaning labels for label-enhanced retrieval, and (2) reranks candidates with a token-level novelty estimator that mitigates auto-regressive continuation bias. Experiments on bilingual datasets across diverse domains show that NovelQR is preferred by human judges and improves overall recommendation quality over strong baselines, while achieving competitive novelty estimation.
(Code: https://anonymous.4open.science/r/NoQuote-3CD0/)

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: re-ranking, retrieval-augmented generation

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources

Languages Studied: English,Chinese

Submission Number: 215