Mashable's Best: E-readers, robovacs, laptops, earbuds, smart home and more Look Up Say More Mashable Selects Mashable Voices Safety Net Creator Hub Versus Gift Ideas For Everyone On Your List Switch Off Trending Now In My Bag All Series Get elegant performance, minus the $400+ price tag. Bethany Allard is a Los Angeles-based shopping reporter at Mashable covering beauty tech, dating, sex and relationships, and headphones. That basically means she puts her hair through a lot, scrolls through a lot of dating apps, and rotates through a lot of different headphones. In addition to testing out and rounding up the best products, she also covers deals for Mashable, paying an especially obsessive amount of attention to Apple deals and prices. That knowledge comes in handy when she's covering shopping holidays like Prime Day and Black Friday, which she's now done for three years at Mashable. All products featured here are independently selected by our editors and writers. If you buy something through links on our site, Mashable may earn an affiliate commission. With Dyson beauty products among the most sought-after (and expensive) on the market, the dupe pool has naturally grown. As a result, my mission to try as many promising Supersonic dupes as possible has become a years-long affair.

Look Up Mashable's Best: E-readers, robovacs, laptops, earbuds, smart home and more Say More Safety Net Creator Hub Versus Gift Ideas For Everyone On Your List Mashable Selects Switch Off Trending Now In My Bag VidCon with Mashable All Series CVS's Epic Beauty Sale is live -- $10 off when you spend $30+ on cosmetics, skin care, hair care, and more This is it -- the time to stock up is now. Soumya is a deals writer who covers consumer tech, shopping deals, and the products people use every day. With experience writing about everything from AI tools and software to smartphones and home gadgets, she enjoys breaking down product research into clear, useful recommendations. When she's not tracking deals, she's usually comparing products, digging through reviews, and figuring out what actually makes a purchase worth it. All products featured here are independently selected by our editors and writers.

It wouldn't be Amazon Prime Day without some beauty deals. Beauty deals are among the few Amazon Prime Day sales that are great nearly across the board. Whereas some tech products are only on sale because they're old, or the deals are the same you can find year-round, the beauty deals we've spotted are almost always on new and trendy products or classics we wouldn't want to go without. We do test a lot of tech professionally, but we apply that same testing protocol to the beauty products we use in our everyday lives. Here are some deals on our tried-and-tested favorites.

It wouldn't be Amazon Prime Day without some beauty deals. Beauty deals are among the few Amazon Prime Day sales that are great nearly across the board. Whereas some tech products are only on sale because they're old, or the deals are the same you can find year-round, the beauty deals we've spotted are almost always on new and trendy products or classics we wouldn't want to go without. We do test a lot of tech professionally, but we apply that same testing protocol to the beauty products we use in our everyday lives. Here are some deals on our tried-and-tested favorites. Make sure to check our list of the Absolute Best Prime Day deals for more verified discounts on the gear we recommend.

With the wide and cross-domain adoption of Large Language Models, it becomes crucial to assess to which extent the statistical correlations in training data, which underlie their impressive performance, hide subtle and potentially troubling biases. Gender bias in LLMs has been widely investigated from the perspectives of works, hobbies, and emotions typically associated with a specific gender. In this study, we introduce a novel perspective. We investigate whether LLMs can predict an individual's gender based solely on online shopping histories and whether these predictions are influenced by gender biases and stereotypes. Using a dataset of historical online purchases from users in the United States, we evaluate the ability of six LLMs to classify gender and we then analyze their reasoning and products-gender co-occurrences. Results indicate that while models can infer gender with moderate accuracy, their decisions are often rooted in stereotypical associations between product categories and gender. Furthermore, explicit instructions to avoid bias reduce the certainty of model predictions, but do not eliminate stereotypical patterns. Our findings highlight the persistent nature of gender biases in LLMs and emphasize the need for robust bias-mitigation strategies.

Recent attempts to integrate large language models (LLMs) into recommender systems have gained momentum, but most remain limited to simple text generation or static prompt-based inference, failing to capture the complexity of user preferences and real-world interactions. This study proposes the Multi-Aspect Driven LLM Agent MADRec, an autonomous LLM-based recommender that constructs user and item profiles by unsupervised extraction of multi-aspect information from reviews and performs direct recommendation, sequential recommendation, and explanation generation. MADRec generates structured profiles via aspect-category-based summarization and applies Re-Ranking to construct high-density inputs. When the ground-truth item is missing from the output, the Self-Feedback mechanism dynamically adjusts the inference criteria. Experiments across multiple domains show that MADRec outperforms traditional and LLM-based baselines in both precision and explainability, with human evaluation further confirming the persuasiveness of the generated explanations.

Recent studies have explored integrating large language models (LLMs) into recommendation systems but face several challenges, including training-induced bias and bottlenecks from serialized architecture. To effectively address these issues, we propose a Query-toRecommendation, a parallel recommendation framework that decouples LLMs from candidate pre-selection and instead enables direct retrieval over the entire item pool. Our framework connects LLMs and recommendation models in a parallel manner, allowing each component to independently utilize its strengths without interfering with the other. In this framework, LLMs are utilized to generate feature-enriched item descriptions and personalized user queries, allowing for capturing diverse preferences and enabling rich semantic matching in a zero-shot manner. To effectively combine the complementary strengths of LLM and collaborative signals, we introduce an adaptive reranking strategy. Extensive experiments demonstrate an improvement in performance up to 57%, while also improving the novelty and diversity of recommendations.

Recent advancements in explainable recommendation have greatly bolstered user experience by elucidating the decision-making rationale. However, the existing methods actually fail to provide effective feedback signals for potentially better or worse generated explanations due to their reliance on traditional supervised learning paradigms in sparse interaction data. To address these issues, we propose a novel human-like feedback-driven optimization framework. This framework employs a dynamic interactive optimization mechanism for achieving human-centered explainable requirements without incurring high labor costs. Specifically, we propose to utilize large language models (LLMs) as human simulators to predict human-like feedback for guiding the learning process. To enable the LLMs to deeply understand the task essence and meet user's diverse personalized requirements, we introduce a human-induced customized reward scoring method, which helps stimulate the language understanding and logical reasoning capabilities of LLMs. Furthermore, considering the potential conflicts between different perspectives of explanation quality, we introduce a principled Pareto optimization that transforms the multi-perspective quality enhancement task into a multi-objective optimization problem for improving explanation performance. At last, to achieve efficient model training, we design an off-policy optimization pipeline. By incorporating a replay buffer and addressing the data distribution biases, we can effectively improve data utilization and enhance model generality. Extensive experiments on four datasets demonstrate the superiority of our approach.