Evidence Before Sampling: Interpretable Implicit Negative Candidate Discovery for Recommendation

2026-10-06

AI Summary

This study addresses the lack of interpretability in implicit negative samples and their misalignment with business objectives in recommender systems. We propose an interpretable negative sampling framework that integrates symbolic rules with large language models (LLMs). Specifically, the method mines statistically grounded negative candidates via symbolic rules, filters high-quality samples through multi-dimensional scoring, and leverages LLMs to generate business-oriented semantic explanations, thereby decoupling negative sample evaluation from downstream performance. Experiments on both industrial B2B and public datasets demonstrate that the proposed framework outperforms existing baselines, achieving a 12.5% improvement in PR-AUC. These results indicate that our approach significantly enhances model training effectiveness and business alignment, particularly in data-sparse scenarios.

Abstract

Recommender systems learn from observed user-item interactions, but explicit negative feedback is often unavailable. Since deep learning models require negative signals for training, negative sampling methods typically treat selected unobserved interactions as negatives. However, a missing interaction does not explain why a user is uninterested in an item or whether there is sufficient evidence to label it negative. This is especially important in business recommendation, where negative signals should be interpretable and aligned with business objectives. We formulate implicit negative candidate discovery to identify unobserved interactions supported by observed customer behavior. We encode these patterns as symbolic rules, score them based on support, informativeness, and product relevance, and rank the retained rules by evidence. An LLM then interprets the retained rules using business objectives and domain knowledge; the interpretations are combined with the statistical evidence in the final report. We evaluate our method in an industrial B2B setting and across five public recommendation datasets. Candidate-quality evaluations in the industrial setting and three public datasets show higher precision than the evaluated baselines, while symbolic selection improves downstream test PR-AUC by 12.5% over random selection with four negatives per positive example in the industrial task. Our results show that negative candidate validity can be evaluated separately from downstream recommendation performance. This distinction enables evidence-based, business-aligned, and explainable negative selection, improving both interpretability and model training in sparse, skewed, real-world recommendation settings.

Problem

• Recommender Systems
• Negative Sampling
• Implicit Negative Discovery
• Interpretability
• Evidence-based Recommendation

Innovation

• Implicit Negative Candidate Discovery
• Symbolic Rules
• Large Language Model
• Interpretable Recommendation
• Evidence-based Negative Sampling