Jianzhe Zhao

Yuting Liu, Jian Guan, Jia-Nan Li et al.

We study the problem of personalization in large language models (LLMs). Prior work predominantly represents user preferences as implicit, model-specific vectors or parameters, yielding opaque ``black-box'' profiles that are difficult to interpret and transfer across models and tasks. In contrast, we advocate natural language as a universal, model- and task-agnostic interface for preference representation. The formulation leads to interpretable and reusable preference descriptions, while naturally supporting continual evolution as new interactions are observed. To learn such representations, we introduce a two-stage training framework that combines supervised fine-tuning on high-quality synthesized data with reinforcement learning to optimize long-term utility and cross-task transferability. Based on this framework, we develop AlignXplore+, a universal preference reasoning model that generates textual preference summaries. Experiments on nine benchmarks show that our 8B model achieves state-of-the-art performanc -- outperforming substantially larger open-source models -- while exhibiting strong transferability across tasks, model families, and interaction formats.

Chu Zhao, Enneng Yang, Yuliang Liang et al.

Graph Neural Networks (GNNs)-based recommendation algorithms typically assume that training and testing data are drawn from independent and identically distributed (IID) spaces. However, this assumption often fails in the presence of out-of-distribution (OOD) data, resulting in significant performance degradation. In this study, we construct a Structural Causal Model (SCM) to analyze interaction data, revealing that environmental confounders (e.g., the COVID-19 pandemic) lead to unstable correlations in GNN-based models, thus impairing their generalization to OOD data. To address this issue, we propose a novel approach, graph representation learning via causal diffusion (CausalDiffRec) for OOD recommendation. This method enhances the model's generalization on OOD data by eliminating environmental confounding factors and learning invariant graph representations. Specifically, we use backdoor adjustment and variational inference to infer the real environmental distribution, thereby eliminating the impact of environmental confounders. This inferred distribution is then used as prior knowledge to guide the representation learning in the reverse phase of the diffusion process to learn the invariant representation. In addition, we provide a theoretical derivation that proves optimizing the objective function of CausalDiffRec can encourage the model to learn environment-invariant graph representations, thereby achieving excellent generalization performance in recommendations under distribution shifts. Our extensive experiments validate the effectiveness of CausalDiffRec in improving the generalization of OOD data, and the average improvement is up to 10.69% on Food, 18.83% on KuaiRec, 22.41% on Yelp2018, and 11.65% on Douban datasets.

Yuting Liu, Jinghao Zhang, Yizhou Dang et al.

Involving collaborative information in Large Language Models (LLMs) is a promising technique for adapting LLMs for recommendation. Existing methods achieve this by concatenating collaborative features with text tokens into a unified sequence input and then fine-tuning to align these features with LLM's input space. Although effective, in this work, we identify two limitations when adapting LLMs to recommendation tasks, which hinder the integration of general knowledge and collaborative information, resulting in sub-optimal recommendation performance. (1) Fine-tuning LLM with recommendation data can undermine its inherent world knowledge and fundamental competencies, which are crucial for interpreting and inferring recommendation text. (2) Incorporating collaborative features into textual prompts disrupts the semantics of the original prompts, preventing LLM from generating appropriate outputs. In this paper, we propose a new paradigm, \textbf{Co}llaborative \textbf{Lo}RA (CoRA), with a collaborative query generator. Rather than input space alignment, this method aligns collaborative information with LLM's parameter space, representing them as incremental weights to update LLM's output. This way, LLM perceives collaborative information without altering its general knowledge and text inference capabilities. Specifically, we employ a collaborative filtering model to extract user and item embeddings and inject them into a set number of learnable queries. We then convert collaborative queries into collaborative weights with low-rank properties and merge the collaborative weights into LLM's weights, enabling LLM to perceive the collaborative signals and generate personalized recommendations without fine-tuning or extra collaborative tokens in prompts. Extensive experiments confirm that CoRA effectively integrates collaborative information into LLM, enhancing recommendation performance.

Chu Zhao, Enneng Yang, Yuliang Liang et al.

Graph Contrastive Learning (GCL) leverages data augmentation techniques to produce contrasting views, enhancing the accuracy of recommendation systems through learning the consistency between contrastive views. However, existing augmentation methods, such as directly perturbing interaction graph (e.g., node/edge dropout), may interfere with the original connections and generate poor contrasting views, resulting in sub-optimal performance. In this paper, we define the views that share only a small amount of information with the original graph due to poor data augmentation as noisy views (i.e., the last 20% of the views with a cosine similarity value less than 0.1 to the original view). We demonstrate through detailed experiments that noisy views will significantly degrade recommendation performance. Further, we propose a model-agnostic Symmetric Graph Contrastive Learning (SGCL) method with theoretical guarantees to address this issue. Specifically, we introduce symmetry theory into graph contrastive learning, based on which we propose a symmetric form and contrast loss resistant to noisy interference. We provide theoretical proof that our proposed SGCL method has a high tolerance to noisy views. Further demonstration is given by conducting extensive experiments on three real-world datasets. The experimental results demonstrate that our approach substantially increases recommendation accuracy, with relative improvements reaching as high as 12.25% over nine other competing models. These results highlight the efficacy of our method.

Chu Zhao, Enneng Yang, Jianzhe Zhao et al.

Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference alignment loss. However, our systematic empirical research and theoretical analysis reveal that DPO tends to amplify spurious correlations caused by environmental confounders during the alignment process, significantly undermining the generalization capability of LLM-based generative recommendation methods in out of distribution (OOD) scenarios. To mitigate this issue, we propose CausalDPO, an extension of DPO that incorporates a causal invariance learning mechanism. This method introduces a backdoor adjustment strategy during the preference alignment phase to eliminate interference from environmental confounders, explicitly models the latent environmental distribution using a soft clustering approach, and enhances robust consistency across diverse environments through invariance constraints. Theoretical analysis demonstrates that CausalDPO can effectively capture users stable preference structures across multiple environments, thereby improving the OOD generalization performance of LLM-based recommendation models. We conduct extensive experiments under four representative distribution shift settings to validate the effectiveness of CausalDPO, achieving an average performance improvement of 17.17% across four evaluation metrics.

Chu Zhao, Enneng Yang, Yuting Liu et al.

Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduce overhead and improve exploration, prior work introduces tree structured rollouts, which share reasoning prefixes and branch at key nodes to improve sampling efficiency. However, this paradigm still faces two challenges: (1) high entropy branching can trigger rollout collapse, where the branching budget concentrates on a few trajectories with consecutive high-entropy segments, rapidly reducing the number of effective branches; (2) early pseudo-labels are noisy and biased, which can induce self-reinforcing overfitting, causing the policy to sharpen prematurely and suppress exploration. To address these issues, we propose Entropy Confidence Hybrid Group Relative Policy Optimization (ECHO). During rollout, ECHO jointly leverages local entropy and group level confidence to adaptively control branch width, and further introduces online confidence-based pruning to terminate persistently low confidence branches, avoiding high entropy traps and mitigating collapse. During policy updates, ECHO employs confidence adaptive clipping and an entropy confidence hybrid advantage shaping approach to enhance training robustness and mitigate early stage bias. Experiments demonstrate that ECHO achieves consistent gains on multiple mathematical and visual reasoning benchmarks, and generalizes more effectively under a limited rollout budget.

Yuting Liu, Yizhou Dang, Yuliang Liang et al.

Recently, sign-aware graph recommendation has drawn much attention as it will learn users' negative preferences besides positive ones from both positive and negative interactions (i.e., links in a graph) with items. To accommodate the different semantics of negative and positive links, existing works utilize two independent encoders to model users' positive and negative preferences, respectively. However, these approaches cannot learn the negative preferences from high-order heterogeneous interactions between users and items formed by multiple links with different signs, resulting in inaccurate and incomplete negative user preferences. To cope with these intractable issues, we propose a novel \textbf{L}ight \textbf{S}igned \textbf{G}raph Convolution Network specifically for \textbf{Rec}ommendation (\textbf{LSGRec}), which adopts a unified modeling approach to simultaneously model high-order users' positive and negative preferences on a signed user-item interaction graph. Specifically, for the negative preferences within high-order heterogeneous interactions, first-order negative preferences are captured by the negative links, while high-order negative preferences are propagated along positive edges. Then, recommendation results are generated based on positive preferences and optimized with negative ones. Finally, we train representations of users and items through different auxiliary tasks. Extensive experiments on three real-world datasets demonstrate that our method outperforms existing baselines regarding performance and computational efficiency. Our code is available at \url{https://anonymous.4open.science/r/LSGRec-BB95}.

Chu Zhao, Enneng Yang, Yuliang Liang et al.

The distributionally robust optimization (DRO)-based graph neural network methods improve recommendation systems' out-of-distribution (OOD) generalization by optimizing the model's worst-case performance. However, these studies fail to consider the impact of noisy samples in the training data, which results in diminished generalization capabilities and lower accuracy. Through experimental and theoretical analysis, this paper reveals that current DRO-based graph recommendation methods assign greater weight to noise distribution, leading to model parameter learning being dominated by it. When the model overly focuses on fitting noise samples in the training data, it may learn irrelevant or meaningless features that cannot be generalized to OOD data. To address this challenge, we design a Distributionally Robust Graph model for OOD recommendation (DRGO). Specifically, our method first employs a simple and effective diffusion paradigm to alleviate the noisy effect in the latent space. Additionally, an entropy regularization term is introduced in the DRO objective function to avoid extreme sample weights in the worst-case distribution. Finally, we provide a theoretical proof of the generalization error bound of DRGO as well as a theoretical analysis of how our approach mitigates noisy sample effects, which helps to better understand the proposed framework from a theoretical perspective. We conduct extensive experiments on four datasets to evaluate the effectiveness of our framework against three typical distribution shifts, and the results demonstrate its superiority in both independently and identically distributed distributions (IID) and OOD.

Pengxiang Lan, Enneng Yang, Yuting Liu et al.

Prompt tuning is a promising method to fine-tune a pre-trained language model without retraining its large-scale parameters. Instead, it attaches a soft prompt to the input text, whereby downstream tasks can be well adapted by merely learning the embeddings of prompt tokens. Nevertheless, existing methods still suffer from two challenges: (i) they are hard to balance accuracy and efficiency. A longer (shorter) soft prompt generally leads to a better(worse) accuracy but at the cost of more (less) training time. (ii)The performance may not be consistent when adapting to different downstream tasks. We attribute it to the same embedding space but responsible for different requirements of downstream tasks. To address these issues, we propose an Efficient Prompt Tuning method (EPT) by multi-space projection and prompt fusion. Specifically, it decomposes a given soft prompt into a shorter prompt and two low-rank matrices, significantly reducing the training time. Accuracy is also enhanced by leveraging low-rank matrices and the short prompt as additional knowledge sources to enrich the semantics of the original short prompt. In addition, we project the soft prompt into multiple subspaces to improve the performance consistency, and then adaptively learn the combination weights of different spaces through a gating network. Experiments on 13 natural language processing downstream tasks show that our method significantly and consistently outperforms 11 comparison methods with the relative percentage of improvements up to 12.9%, and training time decreased by 14%.

Pengxiang Lan, Haoyu Xu, Enneng Yang et al.

Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face two significant issues: (i) They overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions, thus reducing the model's comprehension and effectiveness in complex tasks. (ii) Due to the complexity of downstream tasks, long soft prompt is necessitated to improve performance, but prompt length correlates positively with memory usage and computational costs. Achieving high efficiency and performance remains an ongoing challenge. To address these issues, we propose a novel Low-parameters prompt tuning (LAMP) method, which leverages prompt decomposition and compressed outer product. Specifically, the prompt decomposition module employs Truncated SVD to reduce training parameters and significantly lower the dimensionality of the soft prompt parameter space. It then utilizes a compressed outer product module to facilitate multiple interactions among prompt tokens, exploring their intrinsic associations to enhance knowledge representation. Finally, LAMP uses average pooling to reduce memory usage and training/inference time. Extensive experiments across six architectures and eight datasets demonstrate that LAMP outperforms state-of-the-art PT-based and LoRA-based methods in performance and efficiency.

Jianzhe Zhao, Hailin Zhu, Yu Zhang et al.

Federated efficient fine-tuning has emerged as an approach that leverages distributed data and computational resources across nodes to address the challenges of large-scale fine-tuning and privacy preservation. The Low-Rank Adaptation (LoRA) enables efficient fine-tuning of large-scale pre-trained models by introducing trainable low-rank matrices into weight updates.However, in heterogeneous data scenarios, client drift weakens the generalization of the global model, and local models often fail to meet the personalized needs of individual clients.Moreover, existing federated LoRA efficient fine-tuning techniques overlook fine-grained analysis of the tuning matrices. To address this, we conducted preliminary experiments and found that different LoRA matrices exhibit different sensitivity to changes in the direction and magnitude of their vectors.We thus propose a fine-grained federated LoRA tuning method. By fine-tuning the more sensitive directional vectors in the A matrix, which encode shared knowledge, our method learns shared features more effectively across clients and enhances global generalization. Simultaneously, by fine-tuning the more sensitive magnitude vectors in the B matrix, which encode personalized knowledge, our method better captures personalized knowledge, enabling detailed adaptation to local data. The method uses a pipeline combining global and local optimizers. Global optimization further improves local models, achieving collaborative optimization between global and local levels. This improves both the generalization ability of the global model and the personalized adaptation of local models under heterogeneous data scenarios. Experiments on Databricks-Dolly-15k and Natural Instructions with LLaMA2-7B and Deepseek-7B confirm that our method improves global performance by 0.39% and local performance by 0.59%.

Chu Zhao, Eneng Yang, Yizhou Dang et al.

Heuristic negative sampling enhances recommendation performance by selecting negative samples of varying hardness levels from predefined candidate pools to guide the model toward learning more accurate decision boundaries. However, our empirical and theoretical analyses reveal that unobserved environmental confounders (e.g., exposure or popularity biases) in candidate pools may cause heuristic sampling methods to introduce false hard negatives (FHNS). These misleading samples can encourage the model to learn spurious correlations induced by such confounders, ultimately compromising its generalization ability under distribution shifts. To address this issue, we propose a novel method named Causal Negative Sampling via Diffusion (CNSDiff). By synthesizing negative samples in the latent space via a conditional diffusion process, CNSDiff avoids the bias introduced by predefined candidate pools and thus reduces the likelihood of generating FHNS. Moreover, it incorporates a causal regularization term to explicitly mitigate the influence of environmental confounders during the negative sampling process, leading to robust negatives that promote out-of-distribution (OOD) generalization. Comprehensive experiments under four representative distribution shift scenarios demonstrate that CNSDiff achieves an average improvement of 13.96% across all evaluation metrics compared to state-of-the-art baselines, verifying its effectiveness and robustness in OOD recommendation tasks.

Jianzhe Zhao, Feida Zhu, Lingyan He et al.

With the development of the digital economy, data is increasingly recognized as an essential resource for both work and life. However, due to privacy concerns, data owners tend to maximize the value of data through the circulation of information rather than direct data transfer. Federated learning (FL) provides an effective approach to collaborative training models while preserving privacy. However, as model parameters and training data grow, there are not only real differences in data resources between different data owners, but also mismatches between data and computing resources. These challenges lead to inadequate collaboration among data owners, compute centers, and model owners, reducing the global utility of the three parties and the effectiveness of data assetization. In this work, we first propose a framework for resource-decoupled FL involving three parties. Then, we design a Tripartite Stackelberg Model and theoretically analyze the Stackelberg-Nash equilibrium (SNE) for participants to optimize global utility. Next, we propose the Quality-aware Dynamic Resources-decoupled FL algorithm (QD-RDFL), in which we derive and solve the optimal strategies of all parties to achieve SNE using backward induction. We also design a dynamic optimization mechanism to improve the optimal strategy profile by evaluating the contribution of data quality from data owners to the global model during real training. Finally, our extensive experiments demonstrate that our method effectively encourages the linkage of the three parties involved, maximizing the global utility and value of data assets.