Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2504.05322

Balancing Benefits and Risks: RL Approaches for Addiction-Aware Social Media Recommenders

Luca Bolis·Stefano Livella·Sabrina Patania·Dimitri Ognibene·Matteo Papini·Kenji Morita
View original source ↗Read source document ↗Export metadata ↓

Abstract

Social media platforms provide valuable opportunities for users to gather information, interact with friends, and enjoy entertainment. However, their addictive potential poses significant challenges, including overuse and negative psycho-logical or behavioral impacts [4, 2, 8]. This study explores strategies to mitigate compulsive social media usage while preserving its benefits and ensuring economic sustainability, focusing on recommenders that promote balanced usage. We analyze user behaviors arising from intrinsic diversities and environmental interactions, offering insights for next-generation social media recommenders that prioritize well-being. Specifically, we examine the temporal predictability of overuse and addiction using measures available to recommenders, aiming to inform mechanisms that prevent addiction while avoiding user disengagement [7]. Building on RL-based computational frameworks for addiction modelling [6], our study introduces: - A recommender system adapting to user preferences, introducing non-stationary and non-Markovian dynamics. - Differentiated state representations for users and recommenders to capture nuanced interactions. - Distinct usage conditions-light and heavy use-addressing RL's limitations in distinguishing prolonged from healthy engagement. - Complexity in overuse impacts, highlighting their role in user adaptation [7]. Simulations demonstrate how model-based (MB) and model-free (MF) decision-making interact with environmental dynamics to influence user behavior and addiction. Results reveal the significant role of recommender systems in shaping addiction tendencies or fostering healthier engagement. These findings support ethical, adaptive recommender design, advancing sustainable social media ecosystems [9, 1]. Keywords: multi-agent systems, recommender systems, addiction, social media

Explore related subjects

cs.IRcs.CY

Keep this discovery

BibTeXRIS

Luca Bolis, Stefano Livella, Sabrina Patania, Dimitri Ognibene, Matteo Papini, Kenji Morita. 2025-02-25. Balancing Benefits and Risks: RL Approaches for Addiction-Aware Social Media Recommenders. https://arxiv.org/abs/2504.05322

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems

Industrial recommender systems use cascaded stages with different objectives, feature spaces, and latency constraints. Optimizing pre-ranking and ranking separately can create cross-stage inconsistency: upstream models may filter out items preferred by downstream rankers, and independently tuned downstream fusion can offset upstream improvements. Existing multi-task fusion methods focus on multi-objective fusion within the ranking stage, and cross-stage methods typically only add a downstream score factor to upstream ranking. Joint optimization of fusion modules across both stages remains largely unexplored. We propose UniRec, a Unified Cross-stage Recommendation Fusion model. First, the two fusion agents partially share input embeddings and are trained in a single computation graph, so gradients from either stage propagate through the shared representation and influence the other. Second, we introduce a dual-axis preference alignment objective: a vertical cross-stage consistency term transfers downstream pairwise preferences to the upstream fusion score, and a horizontal compact aggregation term reorganizes dozens of pairwise objectives over heterogeneous prior signals into bidirectional preference evidence. Third, we find that unconstrained end-to-end fusion optimization can exploit imbalances in item attribute distributions, over-concentrating on high-reward regions at the cost of other objectives. We therefore add an attribute group-relative regularization that computes advantages within attribute groups and normalizes the policy over the same groups, so uniformly promoting an entire high-reward group yields no optimization gain. Offline, UniRec consistently outperforms single-stage fusion and cross-stage coordination baselines. Online A/B tests show a 0.616\% gain in app usage duration. UniRec is fully deployed on the Kuaishou platform.

cs.IR↗
arXiv2026

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial token costs. To reduce structural-context tokens without compromising high RAG accuracy, we present {\sf VikingRAG}, a directory-aware semantic data management system that tightly integrates semantic and structural access to support structural-context-efficient, evidence-gap-driven multi-round retrieval. To further reduce token overhead of multi-round interaction, we materialize agentic multi-round retrieval traces as experience edges, and reuse these edges for similar queries, avoiding repeated multi-round exploration. To additionally reduce token costs when agentic multi-round retrieval is unnecessary, we introduce an adaptive escalation strategy that answers from one-round experience-augmented retrieval when the evidence is sufficient, and invokes agentic multi-round retrieval only otherwise. Experiments on real datasets show that the base system {\sf VikingRAG} matches high accuracy of state-of-the-art methods while consuming only 11.6\%--51.9\% of their tokens. With retrieval-trace reuse and adaptive escalation, token costs drop to 5.1\%--32.5\% while maintaining competitive accuracy and practical document-storage performance, showing the utility of this work for emerging AI knowledge bases.

cs.IR↗
arXiv2026

TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents

Although large language models (LLMs) and retrieval-augmented generation (RAG) have advanced open-domain question answering (QA), they remain unreliable when documents evolve through amendments. Existing time-sensitive retrieval methods address only the disjoint-evolving environment, where each update is an independent snapshot. However, laws, policies, and regulations often operate in overlapping-evolving environments, where amendments override earlier clauses while preserving most content, creating strong semantic overlap across versions. We propose TimelyRAG, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents. We also introduce TimelyQABench, the first benchmark for regulation-heavy domains with overlapping-evolving challenges. Experiments show consistent gains, up to +28.6% in nDCG@10, highlighting the importance of temporal reasoning for reliable QA over evolving documents. All resources are available at https://github.com/kaist-dmlab/TimelyRAG.

cs.IR↗