Every Preference Has Its Strength: Injecting Ordinal Semantics into LLM-Based Recommenders

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jeong, Jiwon, Han, Donghee, Hong, Sungrae, Kang, Woosung, Yi, Mun Yong
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909031607566336
author Jeong, Jiwon
Han, Donghee
Hong, Sungrae
Kang, Woosung
Yi, Mun Yong
author_facet Jeong, Jiwon
Han, Donghee
Hong, Sungrae
Kang, Woosung
Yi, Mun Yong
contents Recent work has shown that large language models (LLMs) can enhance recommender systems by integrating collaborative filtering (CF) signals through hybrid prompting. However, most existing CF-LLM frameworks collapse explicit ratings into implicit or positive-only feedback, discarding the ordinal structure that conveys fine-grained preference strength. As a result, these models struggle to exploit graded semantics and nuanced preference distinctions. We propose Ordinal Semantic Anchoring (OSA), a hybrid CF-LLM framework that explicitly incorporates preference strength by modeling interaction-level user feedback. OSA represents ordinal preference levels as numeric textual tokens and uses their token embeddings as semantic anchors to align user-item interaction representations in the LLM latent space. Through strength-aware alignment across ordinal levels, OSA preserves preference semantics when integrating collaborative signals with LLMs. Experiments on multiple real-world datasets demonstrate that OSA consistently outperforms existing baselines, particularly in pairwise preference evaluation, highlighting its effectiveness in modeling fine-grained user preferences over prior CF-LLM methods.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10323
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Every Preference Has Its Strength: Injecting Ordinal Semantics into LLM-Based Recommenders
Jeong, Jiwon
Han, Donghee
Hong, Sungrae
Kang, Woosung
Yi, Mun Yong
Information Retrieval
Recent work has shown that large language models (LLMs) can enhance recommender systems by integrating collaborative filtering (CF) signals through hybrid prompting. However, most existing CF-LLM frameworks collapse explicit ratings into implicit or positive-only feedback, discarding the ordinal structure that conveys fine-grained preference strength. As a result, these models struggle to exploit graded semantics and nuanced preference distinctions. We propose Ordinal Semantic Anchoring (OSA), a hybrid CF-LLM framework that explicitly incorporates preference strength by modeling interaction-level user feedback. OSA represents ordinal preference levels as numeric textual tokens and uses their token embeddings as semantic anchors to align user-item interaction representations in the LLM latent space. Through strength-aware alignment across ordinal levels, OSA preserves preference semantics when integrating collaborative signals with LLMs. Experiments on multiple real-world datasets demonstrate that OSA consistently outperforms existing baselines, particularly in pairwise preference evaluation, highlighting its effectiveness in modeling fine-grained user preferences over prior CF-LLM methods.
title Every Preference Has Its Strength: Injecting Ordinal Semantics into LLM-Based Recommenders
topic Information Retrieval
url https://arxiv.org/abs/2605.10323