arXiv AI
Jun 4
Rethinking Sales Lead Scoring with LLM-based Hierarchical Preference Ranking
arXiv:2606. 04387v1 Announce Type: cross Abstract: Sales lead conversion in high-stakes domains (e.
Beyond Ranking Accuracy: Evaluating LLM-Cited Feature Rationales for Next Basket Repurchase Recommendation
Related stories
arXiv Computation and Language
Oct 1
Decision-Oriented Recommendation Reranking: An Empirical Study of Jev
arXiv:2609.40241v1 Announce Type: cross Abstract: Large language models (LLMs) have shown promise for recommendation reranking, but their use introduces an important tradeoff between recommendation q...
arXiv Machine Learning
Oct 15
Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap
arXiv:2610.19065v1 Announce Type: cross Abstract: Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers...
arXiv AI
Oct 12
FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems
FORTE is a model‑agnostic production framework that discovers, validates, and removes features from industrial recommender systems. It uses efficient perturbation and grouped ablation to evaluate candidate feature sets daily, and lineage tracing to identify all downstream models affected. In two large‑scale systems, FORTE removed up to 43.3% of features without online regressions, cutting trainable parameters by 29.9% and improving serving throughput by 19.8‑25.5%.
arXiv Machine Learning
Jun 2
Machine Learning for Coding Retail Product Names to Consumer-Price Categories: A Rule-plus-Bag-of-Words Pipeline with Reliability-Weighted Human-in-the-Loop Labeling
arXiv:2606. 02004v1 Announce Type: cross Abstract: Consumer-price measurement increasingly draws on alternative data sources -- scanner, web-scraped, and transaction/receipt data.
arXiv AI
Sep 15
Safety as a Constraint: Fine-Tuning a LLM Recommender to Explain Itself
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.
Hugging Face Trending Papers
Oct 13
Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap
Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers have improved. However, GR is not a uniformly stron...
arXiv Computation and Language
Oct 9
Beyond Sequences: Distilling Structured Decision Memory for LLM Recommendation
The paper introduces MARI, a Memory-Augmented Recommendation system that uses a Decision Memory Bank to store Structured Decision Memories (SDMs) capturing users’ goals, constraints, and trade-offs. Unlike prior methods that flatten heterogeneous behaviors into token sequences, MARI retrieves relevant SDMs to enhance LLM reasoning, improving performance on next-item prediction and a new Difficult Choice Prediction task while keeping latency low. The approach also provides interpretable, human-readable insights into user decision-making.
arXiv AI
Oct 5
Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation
The paper introduces PROVE-REC, a two‑pass framework that generates verifiable preference proofs for large language model (LLM) recommendation systems. In Pass A, the model condenses user interaction histories into a compact proof of positive and avoidance claims linked to specific evidence entries. Pass B then uses only this proof and its evidence to predict the next item, ensuring the recommendation follows the reasoning path. Verification steps compare masked evidence and removed claims to confirm grounding and influence, while a ranking‑preservation objective retains useful historical information. Experiments on diverse real‑world datasets show PROVE‑REC outperforms strong baselines by up to 7.45%, producing claims that are both better grounded and more influential to recommendation quality.
arXiv AI
Oct 5
Sensory-Aware Sequential Recommendation via Review-Distilled Representations
The paper introduces ASER, a pipeline that fine‑tunes a large language model to extract sensory attribute‑value pairs (e.g., color: matte black, scent: vanilla) from product reviews and distills them into a compact sensory bank for each catalog item. During recommendation, a frozen backbone uses a lightweight relational metric over this bank, achieving consistent improvements in HR@10 and NDCG@10 across five Amazon domains and four backbones, with evidence‑grounded extractions validated in 94.8% of cases. The study demonstrates that structured, evidence‑based sensory features enhance ranking quality beyond generic non‑sensory controls.
arXiv AI
Jul 28
CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation
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.
arXiv Machine Learning
Aug 31
Timing-Aware Repurchase Prediction for Web-Scale E-Commerce: Survival Models for Multi-Surface Grocery Recommendation
The paper proposes replacing multiple horizon‑specific binary classifiers with a single survival model to predict time‑to‑repurchase in grocery e‑commerce. Empirical analysis shows a slightly decreasing hazard (k≈0.9) and that a Log‑Normal model best fits marginal distributions while Weibull best fits residuals. A single Accelerated Failure Time (AFT) model matches or surpasses per‑horizon classifiers with fewer trees, and a 4‑parameter calibration maps survival CDFs to horizon probabilities without monotonicity violations, revealing a trade‑off between calibration and ranking within the AFT family.