MOSS (Model Sanity Service) is a production framework that embeds LLM-based relevance scoring into a continuous monitoring loop for recommendation, search, and offer surfaces, using targeted sampling, strategy-aware prompting, and structured alerting to diagnose semantic failures. It has been deployed for over six months at a large U.S. retailer, identifying two confirmed serving defects and quantifying a 76.4% reduction in alert rate for a backfill blending fix. Benchmark results show that LLM judges outperform non-LLM baselines on both recommendation and search tasks, demonstrating that a single LLM monitoring framework can deliver actionable quality signals across multiple product discovery surfaces.
By Alina Nesen, Prathyusha Kanmanth Reddy, David Relyea, Rohit Avinash Mujumdar, Samaneh Karimi, Bo Shen, Jordan Hashemi
arXiv:2608.30333v1 Announce Type: cross
Abstract: Next-basket repurchase recommendation is commonly formulated as a ranking task: given a customer's purchase history, the system ranks previously purc...
By Yanan Cao, Anay Dombe, Murali Mohana Krishna Dandu, Shreeranjani Srirangamsridharan, Sinduja Subramaniam, Yogananth Mahalingam, Evren Korpeoglu, Kannan Achan
arXiv:2512. 18390v2 Announce Type: replace Abstract: Organizations often have an incumbent predictive model in production when new data sources become available.
By Vassilis Digalakis Jr, Christophe P\'erignon, S\'ebastien Saurin, Flore Sentenac
The paper investigates the trade‑off of using a shared search‑and‑recommendation index that scores new items purely from features, thereby keeping the index open to unseen items. Experiments on public logs show that a feature‑based tower can match warm‑item performance (Recall@20 0.9595 vs 0.9510) and a lexical baseline, while a full‑catalog check is inconclusive. The study also quantifies the cost of this openness on recommendation quality across several baselines, revealing that exact full‑softmax training improves recall but is impractical at catalog scale.
By Theodore Rogers, Joe Standerfer, Dmitrii Timoshenko, Haoxue Li, Zuhaib Akhtar, Soyoung Yang
The paper demonstrates that the outcome of a forecasting leaderboard is largely determined by the evaluator’s design choices rather than the models themselves. By fixing the data, horizon, and period, the authors varied three key evaluation decisions—unit of analysis, error pooling, and scoring metric—and showed that each can reverse or eliminate the apparent superiority of any forecasting method. The study also evaluates the practical impact of these choices on a deployed system, revealing that the selection rule captures a significant portion of the potential performance gain, and confirms the findings on an external public dataset.
By Md Rezwanul Islam, Wael Mohammed
arXiv:2608. 05207v1 Announce Type: new Abstract: Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning.
By Fangxin Wang, Ziyi Zhang, Diyi Zhuang, Langzhou He, Shiyu Wang, Baichuan Mo, Philip S. Yu
arXiv:2609.37076v1 Announce Type: new
Abstract: Large language models trained on vast corpora inherently risk memorizing harmful content that may later re-emerge in their outputs. To mitigate this is...
By Puning Yang, Qizhou Wang, Junchi Yu, Bo Han, Xiuying Chen
UpgradeBench is a decision‑centric longitudinal benchmark that evaluates how fine‑tuned language‑model specialists should be handled when new base‑model releases occur. It covers four consecutive Qwen releases, a continuation checkpoint, six tasks, two model sizes, and OLMo checkpoints with known training lineage, and examines whether retraining, adapter transfer, or other recovery strategies improve specialist performance. The benchmark reveals that upgrade gains vary by task and release interval, that direct adapter copying is sensitive to pretraining distance, and that teacher relabeling can recover specialists without new annotations.
"whyItMatters":"The study provides actionable insights into the cost‑effective management of specialist models across model releases, showing how to balance retraining effort with performance gains."
By Ye Chen, Weining Zhang
arXiv:2606. 07068v1 Announce Type: new Abstract: Background: Since 1990 many feature selection methods have been proposed across heterogeneous applications.
By Malick Ebiele, Malika Bendechache, Rob Brennan
arXiv:2608.24079v1 Announce Type: cross
Abstract: A shared search-and-recommendation index must score new items from features alone because search has no exploration slot. In a public log covering bo...
By Theodore Rogers, Joe Standerfer, Dmitrii Timoshenko, Haoxue Li, Zuhaib Akhtar, Soyoung Yang
Every supervised fine-tuning run forces the same chain of decisions, such as learning rate, batch size, LoRA or full fine-tuning, how many epochs, which optimiser, and what data to feed the model. Eac...
arXiv:2609.01244v1 Announce Type: new
Abstract: Every supervised fine-tuning run forces the same chain of decisions, such as learning rate, batch size, LoRA or full fine-tuning, how many epochs, whic...
By Charles O'Neill, Mudith Jayasekara, Harry Partridge