F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.
Mixed citations
Llamarec: Two-stage recommendation using large language models for ranking
Mixed citation behavior. Most common role is background (60%).
9
Pith papers citing it
Background
60% of classified citations
citation-role summary
background 3
baseline 1
other 1
citation-polarity summary
representative citing papers
HORIZON creates a cross-domain, long-horizon user modeling benchmark from Amazon Reviews that tests generalization across time, domains, and unseen users, exposing gaps in sequential and LLM-based recommendation models.
A systematic review of over 200 studies concludes that LLMs in recommender systems act as a double-edged sword, creating both opportunities and new risks for trustworthiness.
TimeMM proposes a time-as-operator spectral filtering framework with adaptive mixing and modality routing to model non-stationary multimodal user preferences in recommendation systems.
KnowSA_CKP uses comparative knowledge probing to selectively augment LLM prompts for items with knowledge gaps, improving recommendation accuracy and context efficiency.
This survey organizes generative recommendation into data, model, and task dimensions, identifying five advantages including world knowledge integration and creative generation while noting challenges in benchmarks and efficiency.
RcLLM accelerates generative recommendation inference by 1.31x-9.51x in TTFT through beyond-prefix KV caching, replicated user caches, sharded item caches, affinity scheduling, and selective attention with negligible accuracy loss.
MMA uses LLM agents with RL to rerank candidate pools from first-stage retrievers under missing modalities, reporting 4.0% and 12.7% NDCG@10 gains on OOMA and fixed-pool tasks over baselines.
A distillation technique embeds LLM-generated textual user profiles into efficient sequential recommenders without runtime LLM inference, architectural changes, or fine-tuning.
citing papers explorer
-
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking
F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.
-
HORIZON: A Benchmark for In-the-wild User Behaviour Modeling
HORIZON creates a cross-domain, long-horizon user modeling benchmark from Amazon Reviews that tests generalization across time, domains, and unseen users, exposing gaps in sequential and LLM-based recommendation models.
-
Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges
A systematic review of over 200 studies concludes that LLMs in recommender systems act as a double-edged sword, creating both opportunities and new risks for trustworthiness.
-
TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation
TimeMM proposes a time-as-operator spectral filtering framework with adaptive mixing and modality routing to model non-stationary multimodal user preferences in recommendation systems.
-
Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders
KnowSA_CKP uses comparative knowledge probing to selectively augment LLM prompts for items with knowledge gaps, improving recommendation accuracy and context efficiency.
-
A Survey on Generative Recommendation: Data, Model, and Tasks
This survey organizes generative recommendation into data, model, and task dimensions, identifying five advantages including world knowledge integration and creative generation while noting challenges in benchmarks and efficiency.
-
RcLLM: Accelerating Generative Recommendation via Beyond-Prefix KV Caching
RcLLM accelerates generative recommendation inference by 1.31x-9.51x in TTFT through beyond-prefix KV caching, replicated user caches, sharded item caches, affinity scheduling, and selective attention with negligible accuracy loss.
-
Meta-Modal Agent: Sequential Evidence Routing for Missing-Modality Candidate Reranking
MMA uses LLM agents with RL to rerank candidate pools from first-stage retrievers under missing modalities, reporting 4.0% and 12.7% NDCG@10 gains on OOMA and fixed-pool tasks over baselines.
-
Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation
A distillation technique embeds LLM-generated textual user profiles into efficient sequential recommenders without runtime LLM inference, architectural changes, or fine-tuning.