The paper proposes an incremental recommendation approach that uses a causal model built from existing holdback data to avoid delivering redundant recommendations. By applying a dual‑threshold targeting policy, the system only recommends content when the likelihood of a treated stream is high and the likelihood of an organic stream is low, thereby reducing recommendation impressions by 7% without hurting overall consumption. Joint training with holdback data also improves the calibration of the treated head, suggesting that causal models capture more generalisable representations than purely observational models.
arXiv:2605.27043v2 Announce Type: replace
Abstract: Predictive models trained on observational data often fail to generalise when deployed, especially when the training data is a product of the syste...
By Yorgos Felekis, Michael O'Riordan, Oriol Corcoll, Ciar\'an M. Gilligan-Lee
arXiv:2603. 25126v2 Announce Type: replace-cross Abstract: Multi-Behavior Recommendation (MBR) leverages multiple user interaction types (e.
By Ranxu Zhang, Junjie Meng, Ying Sun, Ziqi Xu, Bing Yin, Hao Li, Yanyong Zhang, Chao Wang
arXiv:2607. 23647v1 Announce Type: cross Abstract: Large language models (LLMs) can summarize heterogeneous user evidence in natural language, but current LLM recommenders often collapse enduring preferences, transient intent, and exposure-induced behavior into one profile.
By Gengyu Zhan
The paper presents a method for fine‑tuning a large language model (LLM) recommender to generate personalized, non‑harmful explanations for its recommendations. By training two LLM‑judge reward models and using constrained GRPO, the authors achieve a significant increase in the PASS rate for all three criteria, from 0.649 to 0.956 on their own judges and from 0.677 to 0.931 on an independent judge. The fine‑tuned model maintains its original recommendation performance, demonstrating that LLM‑based recommenders can be adapted to complex tasks without loss of effectiveness.
By Jiashu He, Emma Yanyang Kong, JJ Tan, David Fagnan
arXiv:2608. 15780v1 Announce Type: cross Abstract: Stale recommendations are a pervasive challenge and a leading source of user complaints on large-scale content platforms.
By Di Bai, Feng Han, Zhenwei Tang, Jintao Liu, Luoshu Wang, Jialu Liu
arXiv:2607. 14161v1 Announce Type: cross Abstract: Pinterest is where people turn inspiration into action as users browse ideas, then take steps toward realization, often by discovering shoppable content.
By Junpeng Hou, XianXing Zhang, Sai Xiao, Derek Cheng, Darren Reger, Olafur Gudmundsson, Mehdi Ben Ayed, Zhiqing Rao, Huizhong Duan
arXiv:2608. 10182v1 Announce Type: cross Abstract: Large-scale targeting and recommendation systems are typically built around predictive scores fed into heuristic or local allocation.
By Changshuai Wei, John Bencina, Phuc Nguyen, Andre Assuncao Silva T Ribeiro, Benjamin Zelditch
arXiv:2609.37800v1 Announce Type: cross
Abstract: Many recommender services repeatedly encounter cold-start cohorts, where new users arrive with little or no interaction history. This creates two cha...
By Serafima Lebedeva, Sumantrak Mukherjee, Ali Arshad Sadal, Ilias Ek\c{s}i, Rahul Sharma, Julia Mueller, Theresa Dombrowski, Jakob Karolus, Viktor Bengs, Eyke H\"ullermeier, Sebastian Vollmer
The paper introduces URED (Unexposed Recycling for Efficient Discovery), a training‑free recall‑stage system deployed on Taobao’s feed recommendation platform. URED re‑injects high‑scored but previously unexposed items—discarded by industrial pipelines—into the recall process, achieving a 3.47% increase in discovered categories and an 8.47% boost in content richness while maintaining engagement. The approach relies on a lightweight, production‑validated pipeline that adds less than 1% latency and requires no model retraining, demonstrating significant gains in discovery rate (13.9× platform average) without compromising user engagement.
By Ge Fan, Kai Meng, Huiping Chu, Yuning Jiang, Han Zhu, Bo Zheng
The paper introduces Explanatory World Models (EWM), an attribution framework that leverages explanations from a frontier language model to identify earlier events that plausibly contributed to a delayed outcome. EWM redistributes reward recursively while preserving the undiscounted episode return, and is evaluated on long‑horizon RL benchmarks, a public sequential‑recommendation task, and an industry‑scale generative recommender, consistently outperforming baseline methods, especially when rewards are highly delayed. The study demonstrates that structured explanations can provide reusable credit signals for learning from delayed outcomes.
By Oriol Corcoll, Qiyao Wei, Ciar\'{a}n Mark Gilligan-Lee
arXiv:2607. 03425v1 Announce Type: new Abstract: Algorithmic recourse addresses the challenge of providing tailored recommendations to users affected by unfavorable machine learning decisions, in potentially high-stakes scenarios.
By Denise Tampieri, Giovanni De Toni, Paolo Giudici