Enhancing LLM-Based Recommendations Through Personalized Reasoning

Current recommendation systems powered by large language models (LLMs) often underutilize their reasoning capabilities due to a lack of explicit logical structuring. To address this limitation, we introduce CoT-Rec, a framework that integrates Chain-of-Thought (CoT) reasoning into LLM-driven recommendations by incorporating two crucial processes: user preference analysis and item perception evaluation. CoT-Rec operates in two key phases: (1) personalized data extraction, where user preferences and item perceptions are identified, and (2) personalized data application, where this information is leveraged to refine recommendations. Our experimental analysis demonstrates that CoT-Rec improves recommendation accuracy by making better use of LLMs' reasoning potential. The implementation is publicly available at https://anonymous.4open.science/r/CoT-Rec.

Mitigating Popularity Bias in Collaborative Filtering through Fair Sampling

Recommender systems often suffer from popularity bias, where frequently interacted items are overrepresented in recommendations. This bias stems from propensity factors influencing training data, leading to imbalanced exposure. In this paper, we introduce a Fair Sampling (FS) approach to address this issue by ensuring that both users and items are selected with equal probability as positive and negative instances. Unlike traditional inverse propensity score (IPS) methods, FS does not require propensity estimation, eliminating errors associated with inaccurate calculations. Our theoretical analysis demonstrates that FS effectively neutralizes the influence of propensity factors, achieving unbiased learning. Experimental results validate that FS outperforms state-of-the-art methods in both point-wise and pair-wise recommendation tasks, enhancing recommendation fairness without sacrificing accuracy. The implementation is available at https://anonymous.4open.science/r/Fair-Sampling.

Enhancing Cross-Domain Recommendations with Memory-Optimized LLM-Based User Agents

Large Language Model (LLM)-based user agents have emerged as a powerful tool for improving recommender systems by simulating user interactions. However, existing methods struggle with cross-domain scenarios due to inefficient memory structures, leading to irrelevant information retention and failure to account for social influence factors such as popularity. To address these limitations, we introduce AgentCF++, a novel framework featuring a dual-layer memory architecture and a two-step fusion mechanism to filter domain-specific preferences effectively. Additionally, we propose interest groups with shared memory, allowing the model to capture the impact of popularity trends on users with similar interests. Through extensive experiments on multiple cross-domain datasets, AgentCF++ demonstrates superior performance over baseline models, highlighting its effectiveness in refining user behavior simulation for recommender systems. Our code is available at https://anonymous.4open.science/r/AgentCF-plus.

Oracle-guided Dynamic User Preference Modeling for Sequential Recommendation

Sequential recommendation methods can capture dynamic user preferences from user historical interactions to achieve better performance. However, most existing methods only use past information extracted from user historical interactions to train the models, leading to the deviations of user preference modeling. Besides past information, future information is also available during training, which contains the ``oracle'' user preferences in the future and will be beneficial to model dynamic user preferences. Therefore, we propose an oracle-guided dynamic user preference modeling method for sequential recommendation (Oracle4Rec), which leverages future information to guide model training on past information, aiming to learn ``forward-looking'' models. Specifically, Oracle4Rec first extracts past and future information through two separate encoders, then learns a forward-looking model through an oracle-guiding module which minimizes the discrepancy between past and future information. We also tailor a two-phase model training strategy to make the guiding more effective. Extensive experiments demonstrate that Oracle4Rec is superior to state-of-the-art sequential methods. Further experiments show that Oracle4Rec can be leveraged as a generic module in other sequential recommendation methods to improve their performance with a considerable margin.

DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship

Although there have been automated approaches and tools supporting toxicity censorship for social posts, most of them focus on detection. Toxicity censorship is a complex process, wherein detection is just an initial task and a user can have further needs such as rationale understanding and content modification. For this problem, we conduct a needfinding study to investigate people's diverse needs in toxicity censorship and then build a ChatGPT-based censorship tool named DeMod accordingly. DeMod is equipped with the features of explainable Detection and personalized Modification, providing fine-grained detection results, detailed explanations, and personalized modification suggestions. We also implemented the tool and recruited 35 Weibo users for evaluation. The results suggest DeMod's multiple strengths like the richness of functionality, the accuracy of censorship, and ease of use. Based on the findings, we further propose several insights into the design of content censorship systems.

Constructing and Masking Preference Profile with LLMs for Filtering Discomforting Recommendation

Personalized algorithms can inadvertently expose users to discomforting recommendations, potentially triggering negative consequences. The subjectivity of discomfort and the black-box nature of these algorithms make it challenging to effectively identify and filter such content. To address this, we first conducted a formative study to understand users' practices and expectations regarding discomforting recommendation filtering. Then, we designed a Large Language Model (LLM)-based tool named DiscomfortFilter, which constructs an editable preference profile for a user and helps the user express filtering needs through conversation to mask discomforting preferences within the profile. Based on the edited profile, DiscomfortFilter facilitates the discomforting recommendations filtering in a plug-and-play manner, maintaining flexibility and transparency. The constructed preference profile improves LLM reasoning and simplifies user alignment, enabling a 3.8B open-source LLM to rival top commercial models in an offline proxy task. A one-week user study with 24 participants demonstrated the effectiveness of DiscomfortFilter, while also highlighting its potential impact on platform recommendation outcomes. We conclude by discussing the ongoing challenges, highlighting its relevance to broader research, assessing stakeholder impact, and outlining future research directions.

GraphTransfer: A Generic Feature Fusion Framework for Collaborative Filtering

Graph Neural Networks (GNNs) have demonstrated effectiveness in collaborative filtering tasks due to their ability to extract powerful structural features. However, combining the graph features extracted from user-item interactions and auxiliary features extracted from user genres and item properties remains a challenge. Currently available fusion methods face two major issues: 1) simple methods such as concatenation and summation are generic, but not accurate in capturing feature relationships; 2) task-specific methods like attention mechanisms and meta paths may not be suitable for general feature fusion. To address these challenges, we present GraphTransfer, a simple but universal feature fusion framework for GNN-based collaborative filtering. Our method accurately fuses different types of features by first extracting graph features from the user-item interaction graph and auxiliary features from users and items using GCN. The proposed cross fusion module then effectively bridges the semantic gaps between the interaction scores of different features. Theoretical analysis and experiments on public datasets show that GraphTransfer outperforms other feature fusion methods in CF tasks. Additionally, we demonstrate the universality of our framework via empirical studies in three other scenarios, showing that GraphTransfer leads to significant improvements in the performance of CF algorithms.

AOTree: Aspect Order Tree-based Model for Explainable Recommendation

Recent recommender systems aim to provide not only accurate recommendations but also explanations that help users understand them better. However, most existing explainable recommendations only consider the importance of content in reviews, such as words or aspects, and ignore the ordering relationship among them. This oversight neglects crucial ordering dimensions in the human decision-making process, leading to suboptimal performance. Therefore, in this paper, we propose Aspect Order Tree-based (AOTree) explainable recommendation method, inspired by the Order Effects Theory from cognitive and decision psychology, in order to capture the dependency relationships among decisive factors. We first validate the theory in the recommendation scenario by analyzing the reviews of the users. Then, according to the theory, the proposed AOTree expands the construction of the decision tree to capture aspect orders in users' decision-making processes, and use attention mechanisms to make predictions based on the aspect orders. Extensive experiments demonstrate our method's effectiveness on rating predictions, and our approach aligns more consistently with the user' s decision-making process by displaying explanations in a particular order, thereby enhancing interpretability.

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized models to attain a more efficient and fruitful training strategy. Empirical evidence reveals that when scaling down into network modules, such as heads in self-attention models, we can observe varying learning patterns implicitly associated with each module's trainability. To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue $\lambda_{\max}$. A large $\lambda_{\max}$ indicates that the module learns features with better convergence, while those miniature ones may impact generalization negatively. Inspired by the discovery, we propose a novel training strategy termed Modular Adaptive Training (MAT) to update those modules with their $\lambda_{\max}$ exceeding a dynamic threshold selectively, concentrating the model on learning common features and ignoring those inconsistent ones. Unlike most existing training schemes with a complete BP cycle across all network modules, MAT can significantly save computations by its partially-updating strategy and can further improve performance. Experiments show that MAT nearly halves the computational cost of model training and outperforms the accuracy of baselines.

Negating Negatives: Alignment without Human Positive Samples via Distributional Dispreference Optimization

Large language models (LLMs) have revolutionized the role of AI, yet also pose potential risks of propagating unethical content. Alignment technologies have been introduced to steer LLMs towards human preference, gaining increasing attention. Despite notable breakthroughs in this direction, existing methods heavily rely on high-quality positive-negative training pairs, suffering from noisy labels and the marginal distinction between preferred and dispreferred response data. Given recent LLMs' proficiency in generating helpful responses, this work pivots towards a new research focus: achieving alignment using solely human-annotated negative samples, preserving helpfulness while reducing harmfulness. For this purpose, we propose Distributional Dispreference Optimization (D$^2$O), which maximizes the discrepancy between the generated responses and the dispreferred ones to effectively eschew harmful information. We theoretically demonstrate that D$^2$O is equivalent to learning a distributional instead of instance-level preference model reflecting human dispreference against the distribution of negative responses. Besides, D$^2$O integrates an implicit Jeffrey Divergence regularization to balance the exploitation and exploration of reference policies and converges to a non-negative one during training. Extensive experiments demonstrate that our method achieves comparable generation quality and surpasses the latest baselines in producing less harmful and more informative responses with better training stability and faster convergence.