BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Wenjie Wang

Wenjie Wang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and LanguageInformation RetrievalArtificial IntelligenceComputer VisionCryptography and Securityeess.SPInformation Theoryastro-ph.IMcs.CYHuman-Computer InteractionMachine Learningmath.ITMultiagent Systems

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
20works
0followers
13topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

20 published item(s)

preprint2026arXiv

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering

Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are autonomously selected by LRMs themselves. However, such autonomous selection often produces inefficient or even erroneous reasoning paths. To make reasoning more reliable and flexible, it is important to develop methods for controlling reasoning strategies. Existing methods struggle to control fine-grained reasoning strategies due to conceptual entanglement in LRMs' hidden states. To address this, we leverage Sparse Autoencoders (SAEs) to decompose strategy-entangled hidden states into a disentangled feature space. To identify the few strategy-specific features from the vast pool of SAE features, we propose SAE-Steering, an efficient two-stage feature identification pipeline. SAE-Steering first recalls features that amplify the logits of strategy-specific keywords, filtering out over 99\% of features, and then ranks the remaining features by their control effectiveness. Using the identified strategy-specific features as control vectors, SAE-Steering outperforms existing methods by over 15\% in control effectiveness. Furthermore, controlling reasoning strategies can redirect LRMs from erroneous paths to correct ones, achieving a 7\% absolute accuracy improvement.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

EVA: Editing for Versatile Alignment against Jailbreaks

Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent defenses typically rely on safety fine-tuning or external filters to reduce the model's likelihood of producing harmful content. While effective to some extent, these methods often incur significant computational overheads and suffer from the safety utility trade-off, degrading the model's performance on benign tasks. To address these challenges, we propose EVA (Editing for Versatile Alignment against Jailbreaks), a novel framework that pioneers the application of direct model editing for safety alignment. EVA reframes safety alignment as a precise knowledge correction task. Instead of retraining massive parameters, EVA identifies and surgically edits specific neurons responsible for the model's susceptibility to harmful instructions, while leaving the vast majority of the model unchanged. By localizing the updates, EVA effectively neutralizes harmful behaviors without compromising the model's general reasoning capabilities. Extensive experiments demonstrate that EVA outperforms baselines in mitigating jailbreaks across both LLMs and VLMs, offering a precise and efficient solution for post-deployment safety alignment.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

FinDeepForecast: A Live Multi-Agent System for Benchmarking Deep Research Agents in Financial Forecasting

Deep Research (DR) Agents powered by advanced Large Language Models (LLMs) have fundamentally shifted the paradigm for completing complex research tasks. Yet, a comprehensive and live evaluation of their forecasting performance on real-world, research-oriented tasks in high-stakes domains (e.g., finance) remains underexplored. We introduce FinDeepForecast, the first live, end-to-end multi-agent system for automatically evaluating DR agents by continuously generating research-oriented financial forecasting tasks. This system is equipped with a dual-track taxonomy, enabling the dynamic generation of recurrent and non-recurrent forecasting tasks at both corporate and macro levels. With this system, we generate FinDeepForecastBench, a weekly evaluation benchmark over a ten-week horizon, encompassing 8 global economies and 1,314 listed companies, and evaluate 13 representative methods. Extensive experiments show that, while DR agents consistently outperform strong baselines, their performance still falls short of genuine forward-looking financial reasoning. We expect the proposed FinDeepForecast system to consistently facilitate future advancements of DR agents in research-oriented financial forecasting tasks. The benchmark and leaderboard are publicly available on the OpenFinArena Platform.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

FinDeepResearch: Evaluating Deep Research Agents in Rigorous Financial Analysis

Deep Research (DR) agents, powered by advanced Large Language Models (LLMs), have recently garnered increasing attention for their capability in conducting complex research tasks. However, existing literature lacks a rigorous and systematic evaluation of DR Agent's capabilities in critical research analysis. To address this gap, we first propose HisRubric, a novel evaluation framework with a hierarchical analytical structure and a fine-grained grading rubric for rigorously assessing DR agents' capabilities in corporate financial analysis. This framework mirrors the professional analyst's workflow, progressing from data recognition to metric calculation, and finally to strategic summarization and interpretation. Built on this framework, we construct a FinDeepResearch benchmark that comprises 64 listed companies from 8 financial markets across 4 languages, encompassing a total of 15,808 grading items. We further conduct extensive experiments on the FinDeepResearch using 16 representative methods, including 6 DR agents, 5 LLMs equipped with both deep reasoning and search capabilities, and 5 LLMs with deep reasoning capabilities only. The results reveal the strengths and limitations of these approaches across diverse capabilities, financial markets, and languages, offering valuable insights for future research and development. The benchmark and evaluation code is publicly available at https://OpenFinArena.com/.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization

Diffusion Vision-Language Models (dVLMs), built upon the non-causal foundations of Diffusion Large Language Models (dLLMs), have demonstrated remarkable efficacy in multimodal tasks by departing from the traditional autoregressive generation paradigm. While dVLMs appear inherently robust against conventional jailbreak tactics, which we categorize as Fixed Prefix Optimization (FPO) (e.g., anchoring responses with "Sure, here is"), this perceived resilience is deceptive. Our investigation into the safety landscape of dVLMs reveals a unique refusal pattern: Immediate Refusal and Progressive Refusal. We find that while FPO-based attacks often fail by triggering the latter, the progressive refinement process itself uncovers a novel, latent attack surface. To exploit this vulnerability, we propose Global Probability Optimization (GPO), a general jailbreak paradigm designed specifically for the denoising trajectory of masked diffusion models. Unlike prefix-based methods, GPO manipulates the global generative dynamics to bypass guardrails in diffusion language models. Building on this, we introduce GPO-V, the first visual-modality jailbreak framework tailored for dVLMs. Empirical results demonstrate that GPO-V produces stealthy perturbations with exceptional cross-model transferability, revealing a critical security gap in non-sequential generative architectures. Our findings underscore the critical urgency of addressing safety alignment in dVLMs. These results necessitate an immediate and fundamental re-evaluation of current defense paradigms to mitigate the unique risks of diffusion-based generation. Our code is available at: https://anonymous.4open.science/r/GPO-V-0250.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

NARRA-Gym for Evaluating Interactive Narrative Agents

Interactive narrative tasks require LLMs to sustain a coherent, evolving story while adapting to a user over multiple turns. However, suitable benchmarks for this setting are limited: existing evaluations often focus on static prompts, isolated story generations, or post-hoc ratings, and therefore miss whether models can jointly manage story generation, long-context state and pacing, character simulation, empathic personalization, and story-grounded artifacts. We introduce NARRA-Gym, an executable evaluation environment that turns a sparse emotional seed into a complete interactive story episode and logs the full model-in-the-loop trajectory, including story construction, memory updates, planning, pacing interventions, and optional artifact synthesis. We evaluate nine frontier LLMs using a controlled LLM-as-judge sweep over eight benchmark personas and a human evaluation in which participants rate customized model outputs. Our results show substantial variation across models, personas, and evaluation dimensions: models that produce fluent stories can still fail on robustness, user experience, or resistance-sensitive personalization. These findings suggest that interactive narrative offers a useful benchmark for evaluating long-horizon, user-adaptive LLM behavior beyond isolated story quality.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models

Large Language Models (LLMs) are increasingly deployed in human-centric applications, yet they often fail to provide substantive emotional support. While Reinforcement Learning (RL) has been utilized to enhance empathy of LLMs, existing reward models typically evaluate empathy from a single perspective, overlooking the inherently bidirectional interaction nature of empathy between the supporter and seeker as defined by Empathy Cycle theory. To address this limitation, we propose Psychology-grounded Empathetic Reward Modeling (PERM). PERM operationalizes empathy evaluation through a bidirectional decomposition: 1) Supporter perspective, assessing internal resonation and communicative expression; 2) Seeker perspective, evaluating emotional reception. Additionally, it incorporates a bystander perspective to monitor overall interaction quality. Extensive experiments on a widely-used emotional intelligence benchmark and an industrial daily conversation dataset demonstrate that PERM outperforms state-of-the-art baselines by over 10\%. Furthermore, a blinded user study reveals a 70\% preference for our approach, highlighting its efficacy in generating more empathetic responses. Our code, dataset, and models are available at https://github.com/ZhengWwwq/PERM.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation

Large Language Models (LLMs) achieve strong performance on standard knowledge evaluation benchmarks, yet recent work shows that their knowledge capabilities remain brittle under question variants that test the same knowledge in different forms. Robustness augmentation of existing knowledge evaluation benchmarks is therefore necessary, but current LLM-assisted generate-then-verify pipelines are costly and difficult to scale due to low-yield variant generation and unreliable variant verification. We propose SAGE (Scalable Automated Generation of Robustness BEnchmarks), a framework for scalable robustness augmentation of knowledge evaluation benchmarks using fine-tuned smaller models. SAGE consists of VariantQual, a rubric-based verifier trained on human-labeled seed data, and VariantGen, a variant generator initialized with supervised fine-tuning and further optimized with reinforcement learning using VariantQual as the reward model. Experiments on HellaSwag show that SAGE constructs a large-scale robustness-augmented benchmark with quality comparable to the human-annotated HellaSwag-Pro at substantially lower cost, while the fine-tuned models further generalize to MMLU without benchmark-specific fine-tuning.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs

Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entries and retrieve them only by semantic similarity. This leads to two key challenges for compositional tasks. Firstly, an agent must identify not only relevant skills but also how they depend on and build upon each other. Secondly, it also makes library maintenance difficult, since the system lacks structural cues for deciding when skills should be merged, split, or removed. We propose SKILLGRAPH, a framework that represents reusable skills as nodes in a directed graph, with typed edges encoding prerequisite, enhancement, and co-occurrence relations. Given a new task, SKILLGRAPH retrieves not just individual skills, but an ordered skill subgraph that can guide multi-step decision making. The graph is continuously updated from agent trajectories and reinforcement learning feedback, allowing both the skill library and the agent policy to improve together. Experiments on ALFWorld, WebShop, and seven search-augmented QA tasks show that SKILLGRAPH achieves state-of-the-art performance against memory-augmented RL methods, with especially large gains on complex tasks that require composing multiple skills.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Soft Graph Diffusion Transformer for MIMO Detection

Learning-based MIMO detection has shown strong empirical performance, yet existing methods typically rely on fixed-depth architectures without explicitly modeling the progressive refinement of symbol estimates. In this paper, we revisit MIMO detection from a flow matching perspective and propose the Soft Graph Diffusion Transformer (SGDiT), which reformulates detection as a noise-level-conditioned denoising process that progressively transforms a Gaussian initialization toward the posterior conditioned on channel observations. An adaptive layer normalization (AdaLN)-conditioned soft graph transformer is employed to parameterize the denoising dynamics, enabling stage-aware information integration between observation and symbol domains. To better align with the discrete nature of symbol detection, we further adopt a cross-entropy-based training objective that directly models bit-wise posterior probabilities, providing a more suitable inductive bias than conventional regression-based formulations. Experimental results across various MIMO system configurations demonstrate that SGDiT achieves competitive bit error rate (BER) performance compared with representative baselines. Furthermore, the proposed model exhibits good generalization capability across different channel conditions. Overall, the SGDiT framework provides an effective and practical approach for neural MIMO detection.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems

Multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. Recent work has explored self-evolving MAS that automatically optimize agent capabilities or communication topologies. However, existing methods either learn a topology that remains fixed at inference time or adapt only the topology or capability during inference. We empirically and theoretically show that effective test-time evolution requires jointly adapting both axes, but on different time scales: capabilities should update rapidly to handle emerging subtasks, while the topology should evolve more slowly to preserve coordination stability. We then introduce TacoMAS, a test-time co-evolution framework for dynamic MAS. TacoMAS formulates MAS inference as a task of online graph adaptation, where nodes represent agents with role-specific capabilities and edges define their communication topology. During inference, a fast capability loop updates agent expertise using trajectory-level feedback, while a slow meta-LLM-driven topology loop performs agents' birth-death operations on MAS, including edge edit, agent addition, and agent removal. We further show that this fast-slow design drives MAS evolution toward a task-conditioned stable equilibrium. Experiments on four benchmarks demonstrate that TacoMAS outperforms nearly 20 multi-agent baselines, achieving an average improvement of 13.3% over the strongest baseline. The codes are released at https://github.com/chenxu2-gif/TacoMAS-MultiAgent.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation

Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple reference images. Existing VLM-enhanced diffusion models commonly rely on decoupled visual conditioning: semantic ViT features are processed by the VLM for instruction understanding, whereas appearance-rich VAE features are injected later into the diffusion backbone. Despite its intuitive design, this separation makes it difficult for the model to associate each semantically grounded subject with visual details from the correct reference image. As a result, the model may recognize which subject is being referred to, but fail to preserve its identity and fine-grained appearance, leading to attribute leakage and cross-reference confusion in complex multi-reference settings. To address this issue, we propose UniCustom, a unified visual conditioning framework that fuses ViT and VAE features before VLM encoding. This early fusion exposes the VLM to both semantic cues and appearance-rich details, enabling its hidden states to jointly encode the referred subject and corresponding visual appearance with only a lightweight linear fusion layer. To learn such unified representations, we adopt a two-stage training strategy: reconstruction-oriented pretraining that preserves reference-specific appearance details in the fused hidden states, followed by supervised finetuning on single- and multi-reference generation tasks. We further introduce a slot-wise binding regularization that encourages each image slot to preserve low-level details of its corresponding reference, thereby reducing cross-reference entanglement. Experiments on two multi-reference generation benchmarks demonstrate that UniCustom consistently improves subject consistency, instruction following, and compositional fidelity over strong baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

BadBlocks: Lightweight and Stealthy Backdoor Threat in Text-to-Image Diffusion Models

Diffusion models have recently achieved remarkable success in image generation, yet growing evidence shows their vulnerability to backdoor attacks, where adversaries implant covert triggers to manipulate outputs. While existing defenses can detect many such attacks via visual inspection and neural network-based analysis, we identify a more lightweight and stealthy threat, termed BadBlocks. BadBlocks selectively contaminates specific blocks within the UNet architecture while preserving the normal behavior of the remaining components. Compared with prior methods, it requires only about 30% of the computation and 20% of the GPU time, yet achieves high attack success rates with minimal perceptual degradation. Extensive experiments demonstrate that BadBlocks can effectively evade state-of-the-art defenses, particularly attention-based detection frameworks. Ablation studies further reveal that effective backdoor injection does not require fine-tuning the entire network and highlight the critical role of certain layers in backdoor mapping. Overall, BadBlocks substantially lowers the barrier for backdooring large-scale diffusion models, even on consumer-grade GPUs.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization

The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy Optimization (GRPO) has emerged as a pivotal mechanism for eliciting such post-training reasoning capabilities due to its exceptional performance, it remains plagued by significant training instability and poor sample efficiency. We theoretically identify the root cause of these issues as the lack of distinctiveness within on-policy rollouts: for routine queries, highly homogeneous samples induce destructive gradient conflicts; whereas for hard queries, the scarcity of valid positive samples results in ineffective optimization. To bridge this gap, we propose Distinctiveness-aware Group Relative Policy Optimization (DaGRPO). DaGRPO incorporates two core mechanisms: (1) Sequence-level Gradient Rectification, which utilizes fine-grained scoring to dynamically mask sample pairs with low distinctiveness, thereby eradicating gradient conflicts at the source; and (2) Off-policy Data Augmentation, which introduces high-quality anchors to recover training signals for challenging tasks. Extensive experiments across 9 mathematical reasoning and out-of-distribution (OOD) generalization benchmarks demonstrate that DaGRPO significantly surpasses existing SFT, GRPO, and hybrid baselines, achieving new state-of-the-art performance (e.g., a +4.7% average accuracy gain on math benchmarks). Furthermore, in-depth analysis confirms that DaGRPO effectively mitigates gradient explosion and accelerates the emergence of long-chain reasoning capabilities.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Proactive Recommendation in Social Networks: Steering User Interest with Causal Inference

Recommending items that solely cater to users' historical interests narrows users' horizons. Recent works have considered steering target users beyond their historical interests by directly adjusting items exposed to them. However, the recommended items for direct steering might not align perfectly with the evolution of users' interests, detrimentally affecting the target users' experience. To avoid this issue, we propose a new task named Proactive Recommendation in Social Networks (PRSN) that indirectly steers users' interest by utilizing the influence of social neighbors, i.e., indirect steering by adjusting the exposure of a target item to target users' neighbors. The key to PRSN lies in answering an interventional question: what would a target user' s feedback be on a target item if the item is exposed to the user' s different neighbors? To answer this question, we resort to causal inference and formalize PRSN as: (1) estimating the potential feedback of a user on an item, under the network interference by the item' s exposure to the user' s neighbors; and (2) adjusting the exposure of a target item to target users' neighbors to trade off steering performance and the damage to the neighbors' experience. To this end, we propose a Neighbor Interference Recommendation (NIRec) framework with two modules: (1) an interference representation-based estimation module for modeling potential feedback; (2) a post-learning-based optimization module for adjusting a target item' s exposure to trade off steering performance and the neighbors' experience through greedy search. We conduct extensive semi-simulation experiments on real-world datasets, validating the steering effectiveness of NIRec.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems

As the focus on Large Language Models (LLMs) in the field of recommendation intensifies, the optimization of LLMs for recommendation purposes (referred to as LLM4Rec) assumes a crucial role in augmenting their effectiveness in providing recommendations. However, existing approaches for LLM4Rec often assess performance using restricted sets of candidates, which may not accurately reflect the models' overall ranking capabilities. In this paper, our objective is to investigate the comprehensive ranking capacity of LLMs and propose a two-step grounding framework known as BIGRec (Bi-step Grounding Paradigm for Recommendation). It initially grounds LLMs to the recommendation space by fine-tuning them to generate meaningful tokens for items and subsequently identifies appropriate actual items that correspond to the generated tokens. By conducting extensive experiments on two datasets, we substantiate the superior performance, capacity for handling few-shot scenarios, and versatility across multiple domains exhibited by BIGRec. Furthermore, we observe that the marginal benefits derived from increasing the quantity of training samples are modest for BIGRec, implying that LLMs possess the limited capability to assimilate statistical information, such as popularity and collaborative filtering, due to their robust semantic priors. These findings also underline the efficacy of integrating diverse statistical information into the LLM4Rec framework, thereby pointing towards a potential avenue for future research. Our code and data are available at https://github.com/SAI990323/Grounding4Rec.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A flexible method for estimating luminosity functions via Kernel Density Estimation -- II. Generalization and Python implementation

We propose a generalization of our previous KDE (kernel density estimation) method for estimating luminosity functions (LFs). This new upgrade further extend the application scope of our KDE method, making it a very flexible approach which is suitable to deal with most of bivariate LF calculation problems. From the mathematical point of view, usually the LF calculation can be abstracted as a density estimation problem in the bounded domain of $\{Z_1<z<Z_2,~ L>f_{\mathrm{lim}}(z) \}$. We use the transformation-reflection KDE method ($\hatϕ$) to solve the problem, and introduce an approximate method ($\hatϕ_{\mathrm{1}}$) based on one-dimensional KDE to deal with the small sample size case. In practical applications, the different versions of LF estimators can be flexibly chosen according to the Kolmogorov-Smirnov test criterion. Based on 200 simulated samples, we find that for both cases of dividing or not dividing redshift bins, especially for the latter, our method performs significantly better than the traditional binning method $\hatϕ_{\mathrm{bin}}$. Moreover, with the increase of sample size $n$, our LF estimator converges to the true LF remarkably faster than $\hatϕ_{\mathrm{bin}}$. To implement our method, we have developed a public, open-source Python Toolkit, called \texttt{kdeLF}. With the support of \texttt{kdeLF}, our KDE method is expected to be a competitive alternative to existing nonparametric estimators, due to its high accuracy and excellent stability. \texttt{kdeLF} is available at \url{http://github.com/yuanzunli/kdeLF} with extensive documentation available at \url{http://kdelf.readthedocs.org/en/latest~}.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

An Efficient Two-Stage SPARC Decoder for Massive MIMO Unsourced Random Access

In this paper, we study a concatenate coding scheme based on sparse regression code (SPARC) and tree code for unsourced random access in massive multiple-input and multiple-output systems. Our focus is concentrated on efficient decoding for the inner SPARC with practical concerns. A two-stage method is proposed to achieve near-optimal performance while maintaining low computational complexity. Specifically, a one-step thresholding-based algorithm is first used for reducing large dimensions of the SPARC decoding, after which a relaxed maximum-likelihood estimator is employed for refinement. Adequate simulation results are provided to validate the near-optimal performance and the low computational complexity. Besides, for covariance-based sparse recovery method, theoretical analyses are given to characterize the upper bound of the number of active users supported when convex relaxation is considered, and the probability of successful dimension reduction by the one-step thresholding-based algorithm.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

User-controllable Recommendation Against Filter Bubbles

Recommender systems usually face the issue of filter bubbles: overrecommending homogeneous items based on user features and historical interactions. Filter bubbles will grow along the feedback loop and inadvertently narrow user interests. Existing work usually mitigates filter bubbles by incorporating objectives apart from accuracy such as diversity and fairness. However, they typically sacrifice accuracy, hurting model fidelity and user experience. Worse still, users have to passively accept the recommendation strategy and influence the system in an inefficient manner with high latency, e.g., keeping providing feedback (e.g., like and dislike) until the system recognizes the user intention. This work proposes a new recommender prototype called UserControllable Recommender System (UCRS), which enables users to actively control the mitigation of filter bubbles. Functionally, 1) UCRS can alert users if they are deeply stuck in filter bubbles. 2) UCRS supports four kinds of control commands for users to mitigate the bubbles at different granularities. 3) UCRS can respond to the controls and adjust the recommendations on the fly. The key to adjusting lies in blocking the effect of out-of-date user representations on recommendations, which contains historical information inconsistent with the control commands. As such, we develop a causality-enhanced User-Controllable Inference (UCI) framework, which can quickly revise the recommendations based on user controls in the inference stage and utilize counterfactual inference to mitigate the effect of out-of-date user representations. Experiments on three datasets validate that the UCI framework can effectively recommend more desired items based on user controls, showing promising performance w.r.t. both accuracy and diversity.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Denoising Implicit Feedback for Recommendation

The ubiquity of implicit feedback makes them the default choice to build online recommender systems. While the large volume of implicit feedback alleviates the data sparsity issue, the downside is that they are not as clean in reflecting the actual satisfaction of users. For example, in E-commerce, a large portion of clicks do not translate to purchases, and many purchases end up with negative reviews. As such, it is of critical importance to account for the inevitable noises in implicit feedback for recommender training. However, little work on recommendation has taken the noisy nature of implicit feedback into consideration. In this work, we explore the central theme of denoising implicit feedback for recommender training. We find serious negative impacts of noisy implicit feedback,i.e., fitting the noisy data prevents the recommender from learning the actual user preference. Our target is to identify and prune noisy interactions, so as to improve the quality of recommender training. By observing the process of normal recommender training, we find that noisy feedback typically has large loss values in the early stages. Inspired by this observation, we propose a new training strategy namedAdaptive Denoising Training(ADT), which adaptively prunes noisy interactions during training. Specifically, we devise two paradigms for adaptive loss formulation: Truncated Loss that discards the large-loss samples with a dynamic threshold in each iteration; and reweighted Loss that adaptively lowers the weight of large-loss samples. We instantiate the two paradigms on the widely used binary cross-entropy loss and test the proposed ADT strategies on three representative recommenders. Extensive experiments on three benchmarks demonstrate that ADT significantly improves the quality of recommendation over normal training.

0 citations0 reviewsNo code linkedOpen access