cs.IR · 2026-09-01 · No. 102
Information Retrieval, 2026-09-01.
3 new papers in cs.IR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
3 entries-
01
Learning from What You Retrieve: Online RL Fine-Tuning for Semantic Retrieval
Shaowei Wei, Chong Huang, Songtao Fang, Jin Zhang, Zhuojun Wang, Chengfu Huo
cs.IR · cs.AI
In large-scale e-commerce retrieval, dual-encoder retrievers are op- timized for contrastive similarity, whereas downstream rerankers capture finer-grained relevance preferences; this objective mis- match limits end-to-end retrieval quality. Reinforcement Learning offers a way to use reward-model feedback for retriever adaptation, but we observe that standard policy-gradient updates can degrade embedding geometry, especially when the document...
-
02
Generative Retrieval for E-commerce: Jointly Learning Embedding and Codebook with Same Product Cluster
Songtao Fang, Zihao Xu, Shaowei Wei, Jin Zhang, Zhuojun Wang
cs.IR · cs.AI
With the development of large language models (LLMs), generative retrieval is becoming increasingly important in e-commerce scenarios. Current mainstream approaches typically use a two-stage training strategy: first train a product embedding model, and then learn a codebook that maps embeddings to product IDs. This cascaded approach suffers from two major issues: (1) error accumulation-if the embedding model in the first stage produces biased...
-
03
Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval
Gaoming Zhang, Angqing Jiang, Jianchun Song, Kena Qi, Dayao Chen, Wei Lin, Defu Lian
cs.IR · cs.AI
Generative Retrieval (GR) has emerged as a promising paradigm by mapping queries directly to Semantic IDs (SIDs) with powerful representation capabilities for candidate items. However, existing SIDs derived solely from item content create a semantic gap, failing to align dynamic query intents with static item representations. Furthermore, current generative paradigms rarely model user behavior sequences and are always bottlenecked by the high...
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.