Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration

• URL: http://arxiv.org/abs/2604.17459v1
• Date: Sun, 19 Apr 2026 14:19:28 GMT
• Title: Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration
• Abstract summary: We introduce a novel framework that integrates end-to-cloud collaboration, multimodal perception, and multi-agent orchestration.<n>Our system employs a fact-grounded adjudication pipeline to eliminate inferential hallucinations.<n>It constructs a dynamic, two-tier preference graph that allows for explicit, human-in-the-loop modifications.
• Score: 48.028080782524064
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While personalized recommender systems excel at content discovery, they frequently expose users to undesirable or discomforting information, highlighting the critical need for user-centric filtering tools. Current methods leveraging Large Language Models (LLMs) struggle with two major bottlenecks: they lack multimodal awareness to identify visually inappropriate content, and they are highly prone to "over-association" -- incorrectly generalizing a user's specific dislike (e.g., anxiety-inducing marketing) to block benign, educational materials. These unconstrained hallucinations lead to a high volume of false positives, ultimately undermining user agency. To overcome these challenges, we introduce a novel framework that integrates end-to-cloud collaboration, multimodal perception, and multi-agent orchestration. Our system employs a fact-grounded adjudication pipeline to eliminate inferential hallucinations. Furthermore, it constructs a dynamic, two-tier preference graph that allows for explicit, human-in-the-loop modifications (via Delta-adjustments), explicitly preventing the algorithm from catastrophically forgetting fine-grained user intents. Evaluated on an adversarial dataset comprising 473 highly confusing samples, the proposed architecture effectively curbed over-association, decreasing the false positive rate by 74.3% and achieving nearly twice the F1-Score of traditional text-only baselines. Additionally, a 7-day longitudinal field study with 19 participants demonstrated robust intent alignment and enhanced governance efficiency. User feedback confirmed that the framework drastically improves algorithmic transparency, rebuilds user control, and alleviates the fear of missing out (FOMO), paving the way for transparent human-AI co-governance in personalized feeds.

Related papers

• Verifiable Reasoning for LLM-based Generative Recommendation [106.7765000777685]
  Reasoning in Large Language Models (LLMs) has recently shown strong potential in enhancing generative recommendation.<n>We propose a novel textbftextitreason-verify-recommend paradigm, which interleaves reasoning with verification to provide reliable feedback.<n>Experiments on four real-world datasets demonstrate that VRec substantially enhances recommendation effectiveness and scalability without compromising efficiency.
  arXiv  Detail & Related papers  (2026-03-08T16:55:45Z)
• Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation [60.63465682731118]
  The performance of egocentric AI agents is fundamentally limited by multimodal intent ambiguity.<n>We introduce the Plug-and-Play Clarifier, a zero-shot and modular framework that decomposes the problem into discrete, solvable sub-tasks.<n>Our framework improves the intent clarification performance of small language models by approximately 30%, making them competitive with significantly larger counterparts.
  arXiv  Detail & Related papers  (2025-11-12T04:28:14Z)
• Beyond One-Size-Fits-All: Personalized Harmful Content Detection with In-Context Learning [4.559454504442884]
  We propose a novel framework that unifies the detection of toxicity, spam, and negative sentiment across binary, multi-class, and multi-label settings.<n>Our approach enables lightweight personalization, allowing users to easily block new categories, unblock existing ones, or extend detection to semantic variations.
  arXiv  Detail & Related papers  (2025-10-29T09:11:20Z)
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models [55.30555646945055]
  Text-to-Image (T2I) models are vulnerable to semantic leakage.<n>We introduce DeLeaker, a lightweight approach that mitigates leakage by directly intervening on the model's attention maps.<n>SLIM is the first dataset dedicated to semantic leakage.
  arXiv  Detail & Related papers  (2025-10-16T17:39:21Z)
• AUV-Fusion: Cross-Modal Adversarial Fusion of User Interactions and Visual Perturbations Against VARS [3.68186360493378]
  AUV-Fusion is a cross-modal adversarial attack framework that adopts high-order user preference modeling.<n>We show that AUV-Fusion significantly enhances the exposure of target (cold-start) items compared to conventional baseline methods.
  arXiv  Detail & Related papers  (2025-07-30T17:55:09Z)
• H-NeiFi: Non-Invasive and Consensus-Efficient Multi-Agent Opinion Guidance [26.3381245787395]
  Existing methods often directly modify user views or enforce cross-group connections.<n>We propose the hierarchical, non-intrusive opinion guidance framework, H-NeiFi.<n> Experiments show that H-NeiFi increases consensus speed by 22.0% to 30.7% and maintains global convergence even in the absence of experts.
  arXiv  Detail & Related papers  (2025-07-11T09:56:33Z)
• Multi-agents based User Values Mining for Recommendation [52.26100802380767]
  We propose a zero-shot multi-LLM collaborative framework for effective and accurate user value extraction.<n>We apply text summarization techniques to condense item content while preserving essential meaning.<n>To mitigate hallucinations, we introduce two specialized agent roles: evaluators and supervisors.
  arXiv  Detail & Related papers  (2025-05-02T04:01:31Z)
• Learning Recommender Systems with Soft Target: A Decoupled Perspective [49.83787742587449]
  We propose a novel decoupled soft label optimization framework to consider the objectives as two aspects by leveraging soft labels. We present a sensible soft-label generation algorithm that models a label propagation algorithm to explore users' latent interests in unobserved feedback via neighbors.
  arXiv  Detail & Related papers  (2024-10-09T04:20:15Z)
• Negotiating the Shared Agency between Humans & AI in the Recommender System [1.4249472316161877]
  This study introduces a dual-control mechanism aimed at enhancing user agency.<n>We evaluated the impact of varying levels of transparency and control on user experience.
  arXiv  Detail & Related papers  (2024-03-23T19:23:08Z)
• SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on Twitter [14.483830120541894]
  We propose SeGA, preference-aware self-contrastive learning for anomalous user detection. SeGA uses large language models to summarize user preferences via posts. We empirically validate the effectiveness of the model design and pre-training strategies.
  arXiv  Detail & Related papers  (2023-12-17T05:35:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.