AdaSwitch: Adaptive Switching Generation for Knowledge Distillation

Small language models (SLMs) are crucial for applications with strict latency and computational constraints, yet achieving high performance remains challenging. Knowledge distillation (KD) can transfer capabilities from large teacher models, but existing methods involve trade-offs: off-policy distillation provides high-quality supervision but introduces a training-inference mismatch, while on-policy approaches maintain consistency but rely on low-quality student outputs. To address these issues, we propose AdaSwitch, a novel approach that dynamically combines on-policy and off-policy generation at the token level. AdaSwitch allows the student to first explore its own predictions and then selectively integrate teacher guidance based on real-time quality assessment. This approach simultaneously preserves consistency and maintains supervision quality. Experiments on three datasets with two teacher-student LLM pairs demonstrate that AdaSwitch consistently improves accuracy, offering a practical and effective method for distilling SLMs with acceptable additional overhead.

Empowering Denoising Sequential Recommendation with Large Language Model Embeddings

Sequential recommendation aims to capture user preferences by modeling sequential patterns in user-item interactions. However, these models are often influenced by noise such as accidental interactions, leading to suboptimal performance. Therefore, to reduce the effect of noise, some works propose explicitly identifying and removing noisy items. However, we find that simply relying on collaborative information may result in an over-denoising problem, especially for cold items. To overcome these limitations, we propose a novel framework: Interest Alignment for Denoising Sequential Recommendation (IADSR) which integrates both collaborative and semantic information. Specifically, IADSR is comprised of two stages: in the first stage, we obtain the collaborative and semantic embeddings of each item from a traditional sequential recommendation model and an LLM, respectively. In the second stage, we align the collaborative and semantic embeddings and then identify noise in the interaction sequence based on long-term and short-term interests captured in the collaborative and semantic modalities. Our extensive experiments on four public datasets validate the effectiveness of the proposed framework and its compatibility with different sequential recommendation systems.

Exploring Superior Function Calls via Reinforcement Learning

Function calling capabilities are crucial for deploying Large Language Models in real-world applications, yet current training approaches fail to develop robust reasoning strategies. Supervised fine-tuning produces models that rely on superficial pattern matching, while standard reinforcement learning methods struggle with the complex action space of structured function calls. We present a novel reinforcement learning framework designed to enhance group relative policy optimization through strategic entropy based exploration specifically tailored for function calling tasks. Our approach addresses three critical challenges in function calling: insufficient exploration during policy learning, lack of structured reasoning in chain-of-thought generation, and inadequate verification of parameter extraction. Our two-stage data preparation pipeline ensures high-quality training samples through iterative LLM evaluation and abstract syntax tree validation. Extensive experiments on the Berkeley Function Calling Leaderboard demonstrate that this framework achieves state-of-the-art performance among open-source models with 86.02\% overall accuracy, outperforming standard GRPO by up to 6\% on complex multi-function scenarios. Notably, our method shows particularly strong improvements on code-pretrained models, suggesting that structured language generation capabilities provide an advantageous starting point for reinforcement learning in function calling tasks. We will release all the code, models and dataset to benefit the community.

Measure Domain's Gap: A Similar Domain Selection Principle for Multi-Domain Recommendation

Multi-Domain Recommendation (MDR) achieves the desirable recommendation performance by effectively utilizing the transfer information across different domains. Despite the great success, most existing MDR methods adopt a single structure to transfer complex domain-shared knowledge. However, the beneficial transferring information should vary across different domains. When there is knowledge conflict between domains or a domain is of poor quality, unselectively leveraging information from all domains will lead to a serious Negative Transfer Problem (NTP). Therefore, how to effectively model the complex transfer relationships between domains to avoid NTP is still a direction worth exploring. To address these issues, we propose a simple and dynamic Similar Domain Selection Principle (SDSP) for multi-domain recommendation in this paper. SDSP presents the initial exploration of selecting suitable domain knowledge for each domain to alleviate NTP. Specifically, we propose a novel prototype-based domain distance measure to effectively model the complexity relationship between domains. Thereafter, the proposed SDSP can dynamically find similar domains for each domain based on the supervised signals of the domain metrics and the unsupervised distance measure from the learned domain prototype. We emphasize that SDSP is a lightweight method that can be incorporated with existing MDR methods for better performance while not introducing excessive time overheads. To the best of our knowledge, it is the first solution that can explicitly measure domain-level gaps and dynamically select appropriate domains in the MDR field. Extensive experiments on three datasets demonstrate the effectiveness of our proposed method.

FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement

The integration of large language models (LLMs) with function calling has emerged as a crucial capability for enhancing their practical utility in real-world applications. However, effectively combining reasoning processes with accurate function execution remains a significant challenge. Traditional training approaches often struggle to balance the detailed reasoning steps with the precision of function calls, leading to suboptimal performance. To address these limitations, we introduce FunReason, a novel framework that enhances LLMs' function calling capabilities through an automated data refinement strategy and a Self-Refinement Multiscale Loss (SRML) approach. FunReason leverages LLMs' natural reasoning abilities to generate high-quality training examples, focusing on query parseability, reasoning coherence, and function call precision. The SRML approach dynamically balances the contribution of reasoning processes and function call accuracy during training, addressing the inherent trade-off between these two critical aspects. FunReason achieves performance comparable to GPT-4o while effectively mitigating catastrophic forgetting during fine-tuning. FunReason provides a comprehensive solution for enhancing LLMs' function calling capabilities by introducing a balanced training methodology and a data refinement pipeline. For code and dataset, please refer to our repository at GitHub https://github.com/BingguangHao/FunReason

Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation

Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information. Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system. Building on this foundation, graph-based RAG systems go a step further by retrieving subgraphs, which preserve the relationships between knowledge entities and provide more comprehensive context. However, graph RAG faces two challenges: (1) Retrieving relevant information introduces irrelevant nodes (especially in dense graph databases, where retrieval usually extends to adjacent nodes), and leads to overly lengthy inputs that hinder efficiency; (2) The representation gap between graph and language during generation with LLMs limits the ability to fully leverage graph structures for enhanced understanding. To address these limitations, we propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase. It first formulates a subgraph by retrieving nodes and edges. Then an Aligner is proposed to jointly optimizes a graph encoder with LLM-summarized reasoning. It achieves dual alignment of graph node and representation by leveraging KL divergence loss and contrastive loss, facilitating efficient pruning of irrelevant knowledge and establishing a unified semantic space. The Generator integrates the aligned graph data with LLM to produce coherent and accurate answers. Experiments on GraphQA benchmark across three tasks (including common sense reasoning, scene graph understanding, and knowledge graph reasoning) validate the effectiveness of our method. The code will be available upon accepted.

LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration

Cloud-device collaboration leverages on-cloud Large Language Models (LLMs) for handling public user queries and on-device Small Language Models (SLMs) for processing private user data, collectively forming a powerful and privacy-preserving solution. However, existing approaches often fail to fully leverage the scalable problem-solving capabilities of on-cloud LLMs while underutilizing the advantage of on-device SLMs in accessing and processing personalized data. This leads to two interconnected issues: 1) Limited utilization of the problem-solving capabilities of on-cloud LLMs, which fail to align with personalized user-task needs, and 2) Inadequate integration of user data into on-device SLM responses, resulting in mismatches in contextual user information. In this paper, we propose a Leader-Subordinate Retrieval framework for Privacy-preserving cloud-device collaboration (LSRP), a novel solution that bridges these gaps by: 1) enhancing on-cloud LLM guidance to on-device SLM through a dynamic selection of task-specific leader strategies named as user-to-user retrieval-augmented generation (U-U-RAG), and 2) integrating the data advantages of on-device SLMs through small model feedback Direct Preference Optimization (SMFB-DPO) for aligning the on-cloud LLM with the on-device SLM. Experiments on two datasets demonstrate that LSRP consistently outperforms state-of-the-art baselines, significantly improving question-answer relevance and personalization, while preserving user privacy through efficient on-device retrieval. Our code is available at: https://github.com/Zhang-Yingyi/LSRP.

STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation

Recent deep sequential recommendation models often struggle to effectively model key characteristics of user behaviors, particularly in handling sequence length variations and capturing diverse interaction patterns. We propose STAR-Rec, a novel architecture that synergistically combines preference-aware attention and state-space modeling through a sequence-level mixture-of-experts framework. STAR-Rec addresses these challenges by: (1) employing preference-aware attention to capture both inherently similar item relationships and diverse preferences, (2) utilizing state-space modeling to efficiently process variable-length sequences with linear complexity, and (3) incorporating a mixture-of-experts component that adaptively routes different behavioral patterns to specialized experts, handling both focused category-specific browsing and diverse category exploration patterns. We theoretically demonstrate how the state space model and attention mechanisms can be naturally unified in recommendation scenarios, where SSM captures temporal dynamics through state compression while attention models both similar and diverse item relationships. Extensive experiments on four real-world datasets demonstrate that STAR-Rec consistently outperforms state-of-the-art sequential recommendation methods, particularly in scenarios involving diverse user behaviors and varying sequence lengths.

MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning

There has been a significant increase in the deployment of neural network models, presenting substantial challenges in model adaptation and fine-tuning. Efficient adaptation is crucial in maintaining model performance across diverse tasks and domains. While Low-Rank Adaptation (LoRA) has emerged as a promising parameter-efficient fine-tuning method, its fixed parameter nature limits its ability to handle dynamic task requirements effectively. Adapting models to new tasks can be challenging due to the need for extensive fine-tuning. Current LoRA variants primarily focus on general parameter reduction while overlooking the importance of dynamic parameter adjustment and meta-learning capabilities. Moreover, existing approaches mainly address static adaptations, neglecting the potential benefits of task-aware parameter generation in handling diverse task distributions. To address these limitations, this Ph.D. research proposes a LoRA generation approach to model task relationships and introduces MetaLoRA, a novel parameter-efficient adaptation framework incorporating meta-learning principles. This work develops a comprehensive architecture that integrates meta-parameter generation with adaptive low-rank decomposition, enabling efficient handling of both task-specific and task-agnostic features. MetaLoRA accurately captures task patterns by incorporating meta-learning mechanisms and dynamic parameter adjustment strategies. To our knowledge, this research represents the first attempt to provide a meta-learning enhanced LoRA variant, offering improved adaptation capability while maintaining computational efficiency in model fine-tuning.

Behavior Modeling Space Reconstruction for E-Commerce Search

Delivering superior search services is crucial for enhancing customer experience and driving revenue growth. Conventionally, search systems model user behaviors by combining user preference and query item relevance statically, often through a fixed logical 'and' relationship. This paper reexamines existing approaches through a unified lens using both causal graphs and Venn diagrams, uncovering two prevalent yet significant issues: entangled preference and relevance effects, and a collapsed modeling space. To surmount these challenges, our research introduces a novel framework, DRP, which enhances search accuracy through two components to reconstruct the behavior modeling space. Specifically, we implement preference editing to proactively remove the relevance effect from preference predictions, yielding untainted user preferences. Additionally, we employ adaptive fusion, which dynamically adjusts fusion criteria to align with the varying patterns of relevance and preference, facilitating more nuanced and tailored behavior predictions within the reconstructed modeling space. Empirical validation on two public datasets and a proprietary search dataset underscores the superiority of our proposed methodology, demonstrating marked improvements in performance over existing approaches.