In today's data-rich environment, recommender systems play a crucial role in decision support systems. They provide to users personalized recommendations and explanations about these recommendations. Embedding-based models, despite their widespread use, often suffer from a lack of interpretability, which can undermine trust and user engagement. This paper presents an approach that combines embedding-based and semantic-based models to generate post-hoc explanations in recommender systems, leveraging ontology-based knowledge graphs to improve interpretability and explainability. By organizing data within a structured framework, ontologies enable the modeling of intricate relationships between entities, which is essential for generating explanations. By combining embedding-based and semantic based models for post-hoc explanations in recommender systems, the framework we defined aims at producing meaningful and easy-to-understand explanations, enhancing user trust and satisfaction, and potentially promoting the adoption of recommender systems across the e-commerce sector.
Institute of Software Technology Graz University of Technology（格拉茨工业大学软件技术研究所）；Web Information Systems TU Delft（代尔夫特理工大学网络信息系统系）
Explanations are used in recommender systems for various reasons. Users have to be supported in making (high-quality) decisions more quickly. Developers of recommender systems want to convince users to purchase specific items. Users should better understand how the recommender system works and why a specific item has been recommended. Users should also develop a more in-depth understanding of the item domain. Consequently, explanations are designed in order to achieve specific \emph{goals} such as increasing the transparency of a recommendation or increasing a user's trust in the recommender s…
Universidade Federal do Rio Grande do Sul (UFRGS)（南里奥格兰德联邦大学）；TU Dortmund（多特蒙德工业大学）
With the recent advances in the field of artificial intelligence, an increasing number of decision-making tasks are delegated to software systems. A key requirement for the success and adoption of such systems is that users must trust system choices or even fully automated decisions. To achieve this, explanation facilities have been widely investigated as a means of establishing trust in these systems since the early years of expert systems. With today's increasingly sophisticated machine learning algorithms, new challenges in the context of explanations, accountability, and trust towards such…
Modern recommender systems face an increasing need to explain their recommendations. Despite considerable progress in this area, evaluating the quality of explanations remains a significant challenge for researchers and practitioners. Prior work mainly conducts human study to evaluate explanation quality, which is usually expensive, time-consuming, and prone to human bias. In this paper, we propose an offline evaluation method that can be computed without human involvement. To evaluate an explanation, our method quantifies its counterfactual impact on the recommendation. To validate the effect…
University of Washington（华盛顿大学）；Rutgers University（罗格斯大学）
As recommender systems become increasingly sophisticated and complex, they often suffer from lack of fairness and transparency. Providing robust and unbiased explanations for recommendations has been drawing more and more attention as it can help address these issues and improve trustworthiness and informativeness of recommender systems. However, despite the fact that such explanations are generated for humans who respond more strongly to messages with appropriate emotions, there is a lack of consideration for emotions when generating explanations for recommendations. Current explanation gener…
University of Amsterdam（阿姆斯特丹大学）；Blendle Research（Blendle研究院）
There is an increasing demand for algorithms to explain their outcomes. So far, there is no method that explains the rankings produced by a ranking algorithm. To address this gap we propose LISTEN, a LISTwise ExplaiNer, to explain rankings produced by a ranking algorithm. To efficiently use LISTEN in production, we train a neural network to learn the underlying explanation space created by LISTEN; we call this model Q-LISTEN. We show that LISTEN produces faithful explanations and that Q-LISTEN is able to learn these explanations. Moreover, we show that LISTEN is safe to use in a real world env…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Inria（法国国家信息与自动化研究所）；École Polytechnique（巴黎综合理工学院）
Interpretable explanations for recommender systems and other machine learning models are crucial to gain user trust. Prior works that have focused on paths connecting users and items in a heterogeneous network have several limitations, such as discovering relationships rather than true explanations, or disregarding other users' privacy. In this work, we take a fresh perspective, and present PRINCE: a provider-side mechanism to produce tangible explanations for end-users, where an explanation is defined to be a set of minimal actions performed by the user that, if removed, changes the recommend…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Recent studies have shown that providing personalized explanations alongside recommendations increases trust and perceived quality. Furthermore, it gives users an opportunity to refine the recommendations by critiquing parts of the explanations. On one hand, current recommender systems model the recommendation, explanation, and critiquing objectives jointly, but this creates an inherent trade-off between their respective performance. On the other hand, although recent latent linear critiquing approaches are built upon an existing recommender system, they suffer from computational inefficiency …
Rutgers University（罗格斯大学）；Renmin University of China（中国人民大学）
State-of-the-art recommender systems have the ability to generate high-quality recommendations, but usually cannot provide intuitive explanations to humans due to the usage of black-box prediction models. The lack of transparency has highlighted the critical importance of improving the explainability of recommender systems. In this paper, we propose to extract causal rules from the user interaction history as post-hoc explanations for the black-box sequential recommendation mechanisms, whilst maintain the predictive accuracy of the recommendation model. Our approach firstly achieves counterfac…
From latent factors to language: a user study on LLM-generated explanations for an inherently interpretable matrix-based recommender system
Department of Technological Innovation Management, Faculty of Engineering, University of Mons (UMONS), Mons, Belgium（蒙斯大学工程学院技术创新管理系）；Department of Mathematics and Operational Research, Faculty of Engineering, University of Mons (UMONS), Mons, Belgium（蒙斯大学工程学院数学与运筹学系）；Department of Mathematics（数学系）；Operational Research, Faculty of Engineering, University of Mons (UMONS), Mons, Belgium（运筹学系）
A few Recommender Systems (RS) resort to explanations so as to enhance trust in recommendations. However, current techniques for explanation generation tend to strongly uphold the recommended products instead of presenting both reasons for and reasons against them. We argue that an RS can better enhance overall trust and transparency by frankly displaying both kinds of reasons to users.We have developed such an RS by exploiting knowledge graphs and by applying Snedegar's theory of practical reasoning. We show that our implemented RS has excellent performance and we report on an experiment with…
As with most Machine Learning systems, recommender systems are typically evaluated through performance metrics computed over held-out data points. However, real-world behavior is undoubtedly nuanced: ad hoc error analysis and deployment-specific tests must be employed to ensure the desired quality in actual deployments. In this paper, we propose RecList, a behavioral-based testing methodology. RecList organizes recommender systems by use case and introduces a general plug-and-play procedure to scale up behavioral testing. We demonstrate its capabilities by analyzing known algorithms and black-…
Recommendation to groups of users is a challenging and currently only passingly studied task. Especially the evaluation aspect often appears ad-hoc and instead of truly evaluating on groups of users, synthesizes groups by merging individual preferences. In this paper, we present a user study, recording the individual and shared preferences of actual groups of participants, resulting in a robust, standardized evaluation benchmark. Using this benchmarking dataset, that we share with the research community, we compare the respective performance of a wide range of music group recommendation techni…
Though recommender systems are defined by personalization, recent work has shown the importance of additional, beyond-accuracy objectives, such as fairness. Because users often expect their recommendations to be purely personalized, these new algorithmic objectives must be communicated transparently in a fairness-aware recommender system. While explanation has a long history in recommender systems research, there has been little work that attempts to explain systems that use a fairness objective. Even though the previous work in other branches of AI has explored the use of explanations as a to…
Bar-Ilan University（巴伊兰大学）；Weizmann Institute of Science（魏茨曼科学研究所）
Automated platforms which support users in finding a mutually beneficial match, such as online dating and job recruitment sites, are becoming increasingly popular. These platforms often include recommender systems that assist users in finding a suitable match. While recommender systems which provide explanations for their recommendations have shown many benefits, explanation methods have yet to be adapted and tested in recommending suitable matches. In this paper, we introduce and extensively evaluate the use of "reciprocal explanations" -- explanations which provide reasoning as to why both p…
Insight Centre for Data Analytics（洞察数据分析中心）；University College Dublin（都柏林大学学院）；Aalborg University（奥尔堡大学）
An important task for a recommender system to provide interpretable explanations for the user. This is important for the credibility of the system. Current interpretable recommender systems tend to focus on certain features known to be important to the user and offer their explanations in a structured form. It is well known that user generated reviews and feedback from reviewers have strong leverage over the users' decisions. On the other hand, recent text generation works have been shown to generate text of similar quality to human written text, and we aim to show that generated text can be s…
We present CLEAR, a method for learning session-specific causal graphs, in the possible presence of latent confounders, from attention in pre-trained attention-based recommenders. These causal graphs describe user behavior, within the context captured by attention, and can provide a counterfactual explanation for a recommendation. In essence, these causal graphs allow answering "why" questions uniquely for any specific session. Using empirical evaluations we show that, compared to naively using attention weights to explain input-output relations, counterfactual explanations found by CLEAR are …
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；IIT Bhilai（印度理工学院比莱校区）
System-provided explanations for recommendations are an important component towards transparent and trustworthy AI. In state-of-the-art research, this is a one-way signal, though, to improve user acceptance. In this paper, we turn the role of explanations around and investigate how they can contribute to enhancing the quality of the generated recommendations themselves. We devise a human-in-the-loop framework, called ELIXIR, where user feedback on explanations is leveraged for pairwise learning of user preferences. ELIXIR leverages feedback on pairs of recommendations and explanations to learn…
Existing explainable recommender systems have mainly modeled relationships between recommended and already experienced products, and shaped explanation types accordingly (e.g., movie "x" starred by actress "y" recommended to a user because that user watched other movies with "y" as an actress). However, none of these systems has investigated the extent to which properties of a single explanation (e.g., the recency of interaction with that actress) and of a group of explanations for a recommended list (e.g., the diversity of the explanation types) can influence the perceived explaination qualit…
Stony Brook University（石溪大学）；Sapienza University of Rome（罗马第一大学）；The Xi’an Jiaotong-Liverpool University（西交利物浦大学）；Rutgers University（罗格斯大学）；South China Normal University（华南师范大学）
Recently, graph neural networks (GNNs) have been widely used to develop successful recommender systems. Although powerful, it is very difficult for a GNN-based recommender system to attach tangible explanations of why a specific item ends up in the list of suggestions for a given user. Indeed, explaining GNN-based recommendations is unique, and existing GNN explanation methods are inappropriate for two reasons. First, traditional GNN explanation methods are designed for node, edge, or graph classification tasks rather than ranking, as in recommender systems. Second, standard machine learning e…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Northwestern University（西北大学）；University of Washington & Allen Institute for Artificial Intelligence（华盛顿大学和艾伦人工智能研究所）
Explanations are well-known to improve recommender systems' transparency. These explanations may be local, explaining an individual recommendation, or global, explaining the recommender model in general. Despite their widespread use, there has been little investigation into the relative benefits of these two approaches. Do they provide the same benefits to users, or do they serve different purposes? We conducted a 30-participant exploratory study and a 30-participant controlled user study with a research-paper recommender system to analyze how providing participants local, global, or both expl…
Recommender Systems have been widely used to help users in finding what they are looking for thus tackling the information overload problem. After several years of research and industrial findings looking after better algorithms to improve accuracy and diversity metrics, explanation services for recommendation are gaining momentum as a tool to provide a human-understandable feedback to results computed, in most of the cases, by black-box machine learning techniques. As a matter of fact, explanations may guarantee users satisfaction, trust, and loyalty in a system. In this paper, we evaluate ho…
Understanding why specific items are recommended to users can significantly increase their trust and satisfaction in the system. While neural recommenders have become the state-of-the-art in recent years, the complexity of deep models still makes the generation of tangible explanations for end users a challenging problem. Existing methods are usually based on attention distributions over a variety of features, which are still questionable regarding their suitability as explanations, and rather unwieldy to grasp for an end user. Counterfactual explanations based on a small set of the user's own…
Recommender systems associated with social networks often use social explanations (e.g. "X, Y and 2 friends like this") to support the recommendations. We present a study of the effects of these social explanations in a music recommendation context. We start with an experiment with 237 users, in which we show explanations with varying levels of social information and analyze their effect on users' decisions. We distinguish between two key decisions: the likelihood of checking out the recommended artist, and the actual rating of the artist based on listening to several songs. We find that while…
Despite the potential impact of explanations on decision making, there is a lack of research on quantifying their effect on users' choices. This paper presents an experimental protocol for measuring the degree to which positively or negatively biased explanations can lead to users choosing suboptimal recommendations. Key elements of this protocol include a preference elicitation stage to allow for personalizing recommendations, manual identification and extraction of item aspects from reviews, and a controlled method for introducing bias through the combination of both positive and negative as…
University of New South Wales（新南威尔士大学）；University of Technology Sydney（悉尼科技大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织数据61研究所）
A significant remaining challenge for existing recommender systems is that users may not trust the recommender systems for either lack of explanation or inaccurate recommendation results. Thus, it becomes critical to embrace a trustworthy recommender system. This survey provides a systemic summary of three categories of trust-aware recommender systems: social-aware recommender systems that leverage users' social relationships; robust recommender systems that filter untruthful noises (e.g., spammers and fake information) or enhance attack resistance; explainable recommender systems that provide…
LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning
Monash University（莫纳什大学）；Shanghai University of Finance and Economics（上海财经大学）；Bosch Corporate Research（博世企业研究中心）；Bosch(China) Investment Ltd.（博世（中国）投资有限公司）；BSH Home Appliances Holding (China) Co. Ltd（博世和西门子家用电器集团（中国）控股有限公司）；Griffith University（格里菲斯大学）
Recommender systems employ machine learning models to learn from historical data to predict the preferences of users. Deep neural network (DNN) models such as neural collaborative filtering (NCF) are increasingly popular. However, the tangibility and trustworthiness of the recommendations are questionable due to the complexity and lack of explainability of the models. To enable explainability, recent techniques such as ACCENT and FIA are looking for counterfactual explanations that are specific historical actions of a user, the removal of which leads to a change to the recommendation result. I…
Recommendations with personalized explanations have been shown to increase user trust and perceived quality and help users make better decisions. Moreover, such explanations allow users to provide feedback by critiquing them. Several algorithms for recommender systems with multi-step critiquing have therefore been developed. However, providing a user-friendly interface based on personalized explanations and critiquing has not been addressed in the last decade. In this paper, we introduce four different web interfaces (available under https://lia.epfl.ch/critiquing/) helping users making decisi…
