cs.IR · 2026-08-16 · No. 86
Information Retrieval, 2026-08-16.
2 new papers in cs.IR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
2 entries-
01
Generative Universal Multimodal Retrieval with Dual-role Identifiers
Kaipeng Li, Haitao Yu, Xuanchen Zhou
cs.IR · cs.AI
Generative information retrieval (GIR) has emerged as a compelling alternative to the conventional index-retrieve-then-rank retrieval pipeline by training a generator to produce the identifiers of relevant items directly. Despite its promise, a number of open challenges still remain. First, constrained left-to-right decoding is vulnerable to prefix-level errors and local optima. Second, most prior GIR research remains largely unimodal,...
-
02
FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation
Yuchen Zheng, Sihan Xu, Jingwen Yang, Xiangrui Cai, Haiwei Zhang, Xiaojie Yuan
cs.IR · cs.AI · cs.LG
Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overlooked fairness issue, which we term \textbf{Token Frequency Bias}, where high-frequency SID tokens are systematically over-predicted while low-frequency SID tokens are under-predicted. This bias originates from the combined effects of imbalanced semantic codebooks during SID construction, and...
This edition is part of The Daily Abstract — cs.IR archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.