Sequential recommendation (SR) aims to predict a user's next action by learning from their historical interaction sequences. In real-world applications, these models require periodic updates to adapt to new interactions and evolving user preferences. While incremental learning methods facilitate these updates, they face significant challenges. Replay-based approaches incur high memory and computational costs, and regularization-based methods often struggle to discard outdated or conflicting knowledge. To overcome these challenges, we propose SA-CAISR, a Stage-Adaptive and Conflict-Aware Incremental Sequential Recommendation framework. As a buffer-free framework, SA-CAISR operates using only the old model and new data, directly addressing the high costs of replay-based techniques. SA-CAISR introduces a novel Fisher-weighted knowledge-screening mechanism that dynamically identifies outdated knowledge by estimating parameter-level conflicts between the old model and new data, allowing our approach to selectively remove obsolete knowledge while preserving compatible historical patterns. This dynamic balance between stability and adaptability allows our method to achieve a new state-of-the-art performance in incremental SR. Specifically, SA-CAISR improves Recall@20 by 2.0

Table Question Answering (TQA), which aims to answer natural language questions over tabular data, has recently attracted growing interest in the database community. While state-of-the-art (SOTA) methods based on online Large Language Models (LLMs) achieve remarkable accuracy, they suffer from several drawbacks, including data privacy risks, high latency, high cost, and overthinking due to excessively long reasoning chains. To address these challenges, we propose SPARQ (Sufficient Precise Adaptive Routing for TableQA), a cost-efficient TQA framework designed for robust offline deployment. SPARQ extends the operator pool for table reasoning and introduces an adaptive query routing mechanism that dynamically selects optimal operators, assisted by a verifier with rollback/fallback strategies. Through extensive evaluations, we demonstrate that SPARQ achieves remarkable performance in an offline setting: it improves accuracy by over 5% on WikiTQ and Tab Fact datasets, while reducing the average end-to-end latency by up to 10.19× on consumer-grade hardware (e.g., RTX 4090). To the best of our knowledge, this is the first systematic framework that deploys offline LLMs to achieve SOTA performance for TQA under realistic hardware constraints, balancing both effectiveness and efficiency. Code, full version and artifacts are provided. 11https://github.com/authurlord/SPARQ

Due to the disparity in the amount of semantic information conveyed by images and texts, image-text retrieval (ITR) faces significant difficulties related to semantic capacity imbalance. To tackle semantic capacity imbalance, there are three key challenges in ITR tasks: 1) How to construct a self-adjusting and discriminative semantic measurement unit for semantic capacity balance assessment. 2) How to design a reliable semantic capacity balancing system to accurately measure the degree of semantic capacity balance. 3) How to adaptively supplement missing semantic elements guided by the degree of semantic capacity balance. Therefore, we propose the Adaptive Semantic Supplementation Network (ASSN), which comprises four modules: 1) Construction, 2) Measurement, 3) Supplementation, and 4) Alignment. For the Construction module, dynamic semantic prototypes are constructed as the semantic measurement units for balance quantification. For the Measurement module, visual and textual semantic prototypes are placed on opposite sides of a lever. The distance of each semantic prototype from the pivot is considered as the lever arm, while its cross-modal transformed semantic capacity is regarded as the force. The semantic capacity balance is measured by calculating the torque difference between all semantic prototypes from the two modalities. For the Supplementation module, ASSN iteratively supplements semantic prototypes on the side with smaller total torque. Moreover, ASSN supplements missing semantic elements by retrieving relevant cross-modal neighbors while enforcing a maximum capacity constraint to prevent over-supplementation. This iterative process continues until balance is achieved. For the Alignment module, token features and adaptively supplemented semantic features are aggregated into semantic units to further improve alignment accuracy. Extensive experiments demonstrate the effectiveness of ASSN over state-of-the-art methods.

Editing Large language models (LLMs) with real-world, unstructured knowledge is essential for correcting and updating their internal parametric knowledge. In this work, we revisit the fundamental next-token prediction (NTP) as a candidate paradigm for unstructured editing. We identify Context Reliance as a critical failure mode of NTP-based approaches, where knowledge acquired from edited text becomes highly dependent on its preceding context, leading to recall failures when that context is absent during inference. This hypothesis is supported by our empirical validation that prepending context during inference recovers knowledge recall. We further theoretically demonstrate that Context Reliance is an inherent consequence of gradient-based optimization, which tends to bind acquired knowledge to a specific aggregated contextual representation. To address this, we propose a simple yet effective COntext-INdependent editing framework (COIN), encouraging model to focus on knowledge within local scope rather than memorizing contextual patterns. Evaluations show that COIN reduces Context Reliance by 45.2% and outperforms strong baselines by 23.6% in editing success rate, highlighting the vital role of mitigating Context Reliance for robust editing.

Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often requires post-training or computationally expensive sampling strategies, limiting their practical efficiency. In this work, we first show that a small subset of neurons in LLMs exhibits strong predictive correlations with reasoning correctness. Based on this observation, we propose AdaRAS (Adaptive Reasoning Activation Steering), a lightweight test-time framework that improves reasoning reliability by selectively intervening on neuron activations. AdaRAS identifies Reasoning-Critical Neurons (RCNs) via a polarity-aware mean-difference criterion and adaptively steers their activations during inference, enhancing incorrect reasoning traces while avoiding degradation on already-correct cases. Experiments on 10 mathematics and coding benchmarks demonstrate consistent improvements, including over 13

Generative retrieval models perform document retrieval by autoregressively generating document identifiers (DocIDs). This process naturally forms a sequential decision problem, where each decoding step selects a DocID token and the complete token sequence determines the retrieved document. However, retrieval effectiveness is typically evaluated only after the full DocID is generated, creating a mismatch between token-level generation and document-level relevance supervision. As a result, existing reinforcement learning methods for generative retrieval mostly rely on sequence-level rewards, where the same document-level feedback is propagated to all decoding steps. Such coarse-grained feedback makes it difficult to identify which token decisions are responsible for successful or failed retrieval. In this work, we propose a fine-grained reinforcement learning framework for generative retrieval with token-level relevance rewards. Instead of assigning a single reward to the entire generated DocID, we estimate step-wise rewards by measuring how each token decision changes the expected retrieval quality of the corresponding generation trajectory. This enables more precise credit assignment and encourages the policy to favor token decisions that contribute more directly to document-level relevance. We further develop practical reward estimation strategies tailored to the DocID generation process and incorporate them into a policy optimization framework. Experiments on retrieval benchmarks show that our method consistently outperforms sequence-level reward baselines, demonstrating the effectiveness of fine-grained supervision for aligning autoregressive DocID generation with retrieval objectives.

Knowledge Editing has emerged as a promising solution for efficiently updating embedded knowledge in large language models (LLMs). While existing approaches demonstrate effectiveness in integrating new knowledge and preserving the original capabilities of LLMs, they fail to maintain fine-grained irrelevant knowledge facts that share the same subject as edited knowledge but differ in relation and object. This challenge arises because subject representations inherently encode multiple attributes, causing the target and fine-grained irrelevant knowledge to become entangled in the representation space, and thus vulnerable to unintended alterations during editing. To address this, we propose DiKE, a novel approach that Disentangles Knowledge representations for LLM Editing (DiKE). DiKE consists of two key components: a Knowledge Representation Disentanglement (KRD) module that decomposes the subject representation into target-knowledgerelated and -unrelated components, and a Disentanglement-based Knowledge Edit (DKE) module that updates only the target-related component while explicitly preserving the unrelated one. We further derive a closed-form, rank-one parameter update based on matrix theory to enable efficient and minimally invasive edits. To rigorously evaluate fine-grained irrelevant knowledge preservation, we construct FINE-KED, a new benchmark comprising fine-grained irrelevant knowledge at different levels of relational similarity to the edited knowledge. Extensive experiments across multiple LLMs demonstrate that DiKE substantially improves fine-grained irrelevant knowledge preservation while maintaining competitive general editing performance.

Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream generation, posing a serious security threat for AI applications. Existing RAG injection attacks mainly rely on manipulating external knowledge bases, such as crafting malicious corpus. However, the synthetic text crafted by such data-centric methods could be detectable, leading to the failure of attacks. Beyond corpus manipulation, open-source retrievers are increasingly exposing RAG systems to model-centric attacks. In this paper, we propose conflict-aware retriever editing, i.e., CAREATTACK, a model-centric retriever attack framework for malicious knowledge injection in RAG. Specifically, CAREATTACK consists two stages of conflict-aware retriever editing and attack-preserving anchor repair. Conflict-aware retriever editing adapts efficient closed-form parameter editing to the dense retrieval model, promoting malicious knowledge above benign competing passages and resolving potential parameter conflicts through graph-based conflict detection and parameter editing projection. Then, attack-preserving anchor repair performs lightweight calibration on the edited retriever to further eliminate the impact on non-target prompts while preserving the attack effectiveness for target prompts. We instantiate CAREATTACK on Qwen3-Embedding-0.6B and BGE-M3, and conduct evaluation on three benchmark datasets. Experimental results demonstrate our method substantially promote malicious passages into the retrieved knowledge of RAG systems and can perform attacks for batches of target prompts and passages, given the access of retrieval model parameters. Since most RAG systems are built upon open-source retrieval models, this work reveals a practical attack surface in RAG systems. Codes are public accessible at https://anonymous.4open.science/r/CareAttack-3F1C.

Composed Image Retrieval (CIR) aims to retrieve target images based on a reference image and modified texts. However, existing methods often struggle to extract the correct semantic cues from the reference image that best reflect the user's intent under textual modification prompts, resulting in interference from irrelevant visual noise. In this paper, we propose a novel Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning (MCoT-MVS) for CIR, integrating attention-aware multi-level vision features guided by reasoning cues from a multi-modal large language model (MLLM). Specifically, we leverage an MLLM to perform chain-of-thought reasoning on the multimodal composed input, generating the retained, removed, and target-inferred texts. These textual cues subsequently guide two reference visual attention selection modules to selectively extract discriminative patch-level and instance-level semantics from the reference image. Finally, to effectively fuse these multi-granular visual cues with the modified text and the imagined target description, we design a weighted hierarchical combination module to align the composed query with target images in a unified embedding space. Extensive experiments on two CIR benchmarks, namely CIRR and FashionIQ, demonstrate that our approach consistently outperforms existing methods and achieves new state-of-the-art performance. Code and trained models are publicly released.

Conversational search needs an understanding of the interaction history between users and systems to retrieve information that aligns with the user’s current query. A prominent challenge in this task lies in addressing irrelevant context, which can obscure the user’s true intent and hinder retrieval accuracy. Existing methods for conversational search rely on the dense retrieval architecture, which encodes the context into fixed-length vectors. However, these approaches are constrained by the inherent limitations of the bi-encoder architecture, making it difficult to mitigate interference from irrelevant contexts effectively. In this paper, we propose Conversational Generative Retrieval for Context Denoising (CGR4CD), a novel framework that leverages a sequence-to-sequence generative retrieval architecture with cross-attention layers to dynamically capture key information during decoding. Our method introduces innovative proposition-based docids and a two-stage training strategy, combining generation and rank losses for enhanced denoising and ranking. Extensive evaluations on three conversational search benchmarks (TopiOCQA, QReCC, and OR-QuAC) demonstrate that CGR4CD achieves state-of-the-art performance, outperforming baselines in 8 out of 9 evaluation metrics. On TopiOCQA, which is characterized by topic switching and high noise, CGR4CD achieves an average improvement of 8.2% over baselines of similar size and surpasses the LLM-based Chatretriever by 4.4%, highlighting its superior context denoising capability. Our approach also maintains parameter efficiency, achieving these results with a T5-large backbone compared to larger LLM-based retrievers. Detailed analysis further validates its superior capability in contextual denoising, particularly in noisy scenarios.

Query expansion (QE) is a critical technique in information retrieval that enriches underspecified queries with additional textual context. However, its effect is often unreliable in modern dense retrieval, especially for strong off-the-shelf retrievers without retraining. Existing studies mainly examine expansion quality, semantic drift, or retrieval outcomes, but rarely explain how QE changes dense retrievers internally. In this work, we trace QE effects through sparse autoencoder (SAE) features. Using paired original and expanded queries, we decompose layer-wise retriever representations into sparse latent activations, identify QE-related latents from expansion-induced activation shifts, and interpret them with natural-language descriptions and retrieval cases. Our analysis shows that effective QE induces layer-concentrated changes in sparse latents aligned with retrieval intent and entity attributes, rather than only perturbing final query embeddings. SAE-based activation steering further validates these latents improve retrieval more consistently than random interventions or vanilla QE across four benchmarks, suggesting that SAEs can explain QE effects and offer a lightweight option for precise retrieval behavior modulation without query rewriting or retriever fine-tuning.

Large Language Models have shown great success in recommender systems. However, the limited and sparse nature of user data often restricts the LLM's ability to effectively model behavior patterns. To address this, existing studies have explored cross-domain solutions by conducting Cross-Domain Recommendation tasks. But previous methods typically assume domains are overlapped and can be accessed readily. None of the LLM methods address the privacy-preserving issues in the CDR settings, that is, Privacy-Preserving Cross-Domain Recommendation. Conducting non-overlapping PPCDR with LLM is challenging since: 1)The inability to share user identity or behavioral data across domains impedes effective cross-domain alignment. 2)The heterogeneity of data modalities across domains complicates knowledge integration. 3)Fusing collaborative filtering signals from traditional recommendation models with LLMs is difficult, as they operate within distinct feature spaces. To address the above issues, we propose SF-UBM, a Semantic-enhanced Federated User Behavior Modeling method. Specifically, to deal with Challenge 1, we leverage natural language as a universal bridge to connect disjoint domains via a semantic-enhanced federated architecture. Here, text-based item representations are encrypted and shared, while user-specific data remains local. To handle Challenge 2, we design a Fact-counter Knowledge Distillation module to integrate domain-agnostic knowledge with domain-specific knowledge, across different data modalities. To tackle Challenge 3, we project pre-learned user preferences and cross-domain item representations into the soft prompt space, aligning behavioral and semantic spaces for effective LLM learning. We conduct extensive experiments on three pairs of real-world domains, and the experimental results demonstrate the effectiveness of SF-UBM compared to the recent SOTA methods.

Instruction fine-tuning is employed to enhance the instruction-following ability of large language models (LLMs). As the amount of instruction fine-tuning data increases, selecting the optimal core set becomes particularly important. However, ensuring the diversity of the core set remains a significant challenge. Existing methods predominantly distinguish different training data based on the text features themselves, decoupled from LLMs' own understanding and representation of the data. To address this issue, we propose a Model-Aware Diverse Core Set Selection method, which distinguishes data features based on the neural activation states during LLM inference. This approach serves as an efficient instantiation of coverage-based selection using model-intrinsic activation features to ensure the diversity in the core set. We extensively evaluate our method on six benchmarks that cover five distinct tasks. In our method, the core set selected by the 3B-parameter LLM performs effectively when utilized to fine-tune larger models with 7B, 8B, and 13B parameters. Experimental results on the Alpaca-GPT4 dataset, which comprises 52K instruction-response pairs, show that the core set, sized at 15% of the original dataset and selected by Llama-3.2-3B-Instruct, achieves an average improvement of 2.5% when fine-tuning four larger base models compared with training on the full dataset. The experimental results demonstrate that our method enhances model performance on multiple downstream tasks while reducing data requirements.

The rapid scaling of large language models (LLMs) has made full fine-tuning increasingly impractical due to its prohibitive computational, storage, and memory costs. Although parameter-efficient fine-tuning (PEFT) methods such as Low-Rank Adaptation (LoRA) significantly reduce the number of trainable parameters, most existing approaches treat layers independently and overlook potential cross-layer redundancy. To address this limitation, this paper aims to develop a more parameter-efficient adaptation strategy that can effectively exploit cross-layer parameter sharing while maintaining model expressiveness. Motivated by our preliminary analysis showing that the optimal sharing granularity varies across tasks, we propose ASLoRA, a cross-layer parameter-sharing framework that combines global sharing with partial adaptive sharing. Specifically, ASLoRA introduces a globally shared low-rank input projection (A) together with selectively merged layer-wise output projections (B), enabling the model to balance global parameter reuse with task-specific adaptation. Extensive experiments on diverse NLP benchmarks demonstrate that ASLoRA consistently outperforms standard LoRA while using only about 20% of the trainable parameters. Further analyses show that our proposed adaptive sharing strategy enhances both adaptation capacity and task-specific adaptability.

Sequential knowledge editing in large language models often causes catastrophic collapse of the model’s general abilities, especially for parameter-modifying methods. Existing approaches mitigate this issue through heuristic constraints on parameter updates, the mechanisms underlying such degradation remain insufficiently understood. In this work, we present a systematic spectral analysis of sequential knowledge editing and show that a model’s general abilities are closely associated with dominant singular directions of pretrained weight matrices. These directions are highly sensitive to perturbations and are progressively disrupted by repeated edits, closely tracking the collapse in both editing efficacy and general performance. Building on this insight, we propose REVIVE, a plug-and-play framework that prevents model collapse by explicitly preserving this dominant subspace. REVIVE analyzes parameter updates in the spectral basis of the original weights and filters out components that would interfere with the dominant subspace. Extensive experiments across multiple models and benchmarks show that REVIVE consistently improves editing efficacy while substantially preserving general abilities under long-horizon sequential editing, including extreme settings with up to 20,000 edits.

While generative retrieval (GR) demonstrates competitive performance on standard retrieval benchmarks, existing approaches directly map queries to document identifiers (docids) without intermediate deliberation, limiting their effectiveness for complex queries that require multi-step reasoning. As a preliminary study on integrating chain-of-thought (CoT) into generative retrieval, we introduce ThinkGR, a unified framework that interleaves CoT with docid generation, enabling iterative thinking and retrieval within a single generative process. To bridge the gap between free-form thought generation and structured retrieval targets, we design (1) a hybrid decoding strategy that dynamically switches between unconstrained thought generation and constrained docid decoding, and (2) a two-phase training approach that first aligns thought-retrieval patterns through supervised fine-tuning, then optimizes thought quality via retrieval-grounded reinforcement learning. Experiments on four multi-hop retrieval benchmarks demonstrate that ThinkGR achieves state-of-the-art performance with an average improvement of +6.86%. Our work opens new avenues for enhancing generative retrieval with explicit deliberation capabilities, with promising implications for retrieval tasks requiring complex reasoning.

Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs). Monte Carlo Tree Search (MCTS)-based extensions improve upon vanilla RLVR (e.g., GRPO) by providing tree-based reasoning rollouts that enable fine-grained and segment-level credit assignment. However, existing methods still suffer from limited exploration diversity and inefficient reasoning. To address the above challenges, we propose reinforced efficient reasoning via semantically diverse explorations, i.e., ROSE, for LLMs. To encourage more diverse reasoning exploration, our method incorporates a semantic-entropy-based branching strategy and an 𝜀 -exploration mechanism. The former operates on already sampled reasoning rollouts to capture semantic uncertainty and select branching points with high semantic divergence to generate new successive reasoning paths, whereas the latter stochastically initiates reasoning rollouts from the root, preventing the search process from becoming overly local. To improve efficiency, we design a length-aware segment-level advantage estimator that rewards concise and correct reasoning while penalizing unnecessarily long reasoning chains. Extensive experiments on various mathematical reasoning benchmarks with Qwen and Llama models validate the effectiveness and efficiency of ROSE. Codes are available at https://github.com/ZiqiZhao1/ROSE-rl.

Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewards improves these agents by optimizing them against checkable criteria that translate report quality into reward signals, but its efficiency depends on whether those criteria reliably capture the task scope and evidence needs. Most existing studies ask an LLM to generate rubrics for a given query, but when the model fails to infer the underlying information needs, the generated rubrics may be incomplete and reduce RL efficiency. To obtain more reliable query--rubric supervision, we introduce DeepRubric, a data construction framework that reverses this process: instead of inferring evaluation criteria for a given query, it first determines what an evidence-backed report should be evaluated on and then synthesizes aligned query--rubric pairs from those evaluation targets. Starting from a sampled seed topic, DeepRubric builds an evidence tree by recursively expanding evidence-backed sub-questions, whose leaves serve as atomic and verifiable evaluation targets. It then uses the evidence tree to synthesize the training query and rubrics, ensuring that the reward evaluates exactly the information requested by the query. Using DeepRubric, we construct 9K query--rubric supervision examples and train DeepRubric-8B with rubric-based GRPO, achieving comparable performance to prior open state-of-the-art deep research models across three benchmarks with roughly 13x fewer RL GPU-hours.

Unified Large Language Models (LLMs) have transformed diverse recommendation tasks into a shared “text-to-text” paradigm. However, existing methods primarily face two challenges: 1) joint fine-tuning across highly heterogeneous tasks (e.g., discriminative sequential recommendation versus generative explanation generation) often suffers from the “seesaw effect” due to severe gradient conflicts; and 2) parameter-efficient methods struggle to isolate these task-specific conflicts while preserving the collaborative sharing of underlying general recommendation knowledge. To address these limitations, we propose Rec-MoELoRA, a hybrid fine-tuning framework that seamlessly integrates the mixture-of-experts architecture with low-rank adaptation. Specifically, we devise a soft-decoupling strategy that maintains the updates of most backbone network layers to continuously absorb globally shared knowledge, while exclusively introducing task-motivated low-rank experts into the self-attention layers for physical task isolation. Furthermore, to effectively overcome the prevalent “expert collapse” dilemma, we incorporate a dual regularization strategy of diversity and entropy. Combined with an asymmetric structural prior (e.g., allocating three experts for two tasks), this forces the model to spontaneously evolve a “Shared-Specific” representation pattern. Extensive experiments on real-world e-commerce datasets (Amazon Sports and Beauty) demonstrate that Rec-MoELoRA significantly outperforms the full fine-tuning baseline across core ranking and text generation metrics while introducing only a marginal number of additional parameters (e.g., HR@10 and BLEU-4 improve by 4.3% and 3.7% on the Sports dataset, respectively).