AlpsBench supplies 2500 real-dialogue sequences with verified memories to benchmark LLM extraction, updating, retrieval, and utilization of personalized information.
hub
arXiv preprint arXiv:2505.19092 (2025)
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
Transformer recommenders amplify popularity bias via spectral collapse when scaled; SPRINT constrains attention column-sums and feed-forward spectral norms to improve fairness and scaling behavior.
TF-LLMER resolves optimization barriers in LLM-enhanced recommenders through embedding normalization and Rec-PCA that aligns semantic representations with collaborative co-occurrence graphs.
TriRec is a two-stage LLM-agent recommender that uses item self-promotion followed by platform-level sequential re-ranking to jointly optimize user utility, item exposure, and exposure fairness.
IntuRec anchors LLM latent reasoning for recommendation by deriving an intuition embedding from top-K candidates via self- and cross-attention to initialize more accurate trajectories.
LASAR uses two-stage supervised training plus reinforcement learning to ground semantic IDs, align latent reasoning trajectories to CoT hidden states via KL divergence, and adaptively choose reasoning depth, halving average steps while improving quality on three datasets.
RRCM trains an LLM to dynamically retrieve from collaborative and meta memories using group relative policy optimization driven by final top-k recommendation quality.
PAD-Rec augments standard draft models with item-position and step-position embeddings plus learnable gates, delivering up to 3.1x wall-clock speedup and 5% average gain over strong speculative-decoding baselines on four datasets while largely preserving recommendation quality.
FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.
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.
BLOGER is a bi-level optimization framework that jointly optimizes the tokenizer and recommender for generative recommendation, outperforming prior methods on real-world datasets.
BBDRec applies Brownian bridge diffusion to enable direct item-to-history transitions in sequential recommendation, outperforming prior diffusion and sequential baselines on public datasets.
TARPO is a pure RL framework using a token-wise action router to switch between discrete token generation and latent reasoning in LLMs, with joint optimization showing outperformance on benchmarks.
LLMs show strong exam performance on medical tasks but exhibit a clear gap in accuracy on authentic clinical decision-making as measured by the new MR-Bench benchmark and unified evaluations.
RPORec unifies LLM reasoning with a recommendation head through reasoning-augmented modeling and reinforced preference optimization to improve recommendation accuracy and interpretability.
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.
citing papers explorer
-
AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment
AlpsBench supplies 2500 real-dialogue sequences with verified memories to benchmark LLM extraction, updating, retrieval, and utilization of personalized information.
-
The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders
Transformer recommenders amplify popularity bias via spectral collapse when scaled; SPRINT constrains attention column-sums and feed-forward spectral norms to improve fairness and scaling behavior.
-
Break the Optimization Barrier of LLM-Enhanced Recommenders: A Theoretical Analysis and Practical Framework
TF-LLMER resolves optimization barriers in LLM-enhanced recommenders through embedding normalization and Rec-PCA that aligns semantic representations with collaborative co-occurrence graphs.
-
Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation
TriRec is a two-stage LLM-agent recommender that uses item self-promotion followed by platform-level sequential re-ranking to jointly optimize user utility, item exposure, and exposure fairness.
-
Intuition-Guided Latent Reasoning for LLM-Based Recommendation
IntuRec anchors LLM latent reasoning for recommendation by deriving an intuition embedding from top-K candidates via self- and cross-attention to initialize more accurate trajectories.
-
LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation
LASAR uses two-stage supervised training plus reinforcement learning to ground semantic IDs, align latent reasoning trajectories to CoT hidden states via KL divergence, and adaptively choose reasoning depth, halving average steps while improving quality on three datasets.
-
RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
RRCM trains an LLM to dynamically retrieve from collaborative and meta memories using group relative policy optimization driven by final top-k recommendation quality.
-
Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation
PAD-Rec augments standard draft models with item-position and step-position embeddings plus learnable gates, delivering up to 3.1x wall-clock speedup and 5% average gain over strong speculative-decoding baselines on four datasets while largely preserving recommendation quality.
-
Factorized Latent Reasoning for LLM-based Recommendation
FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.
-
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.
-
Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation
BLOGER is a bi-level optimization framework that jointly optimizes the tokenizer and recommender for generative recommendation, outperforming prior methods on real-world datasets.
-
Brownian Bridge Diffusion for Sequential Recommendation
BBDRec applies Brownian bridge diffusion to enable direct item-to-history transitions in sequential recommendation, outperforming prior diffusion and sequential baselines on public datasets.
-
TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization
TARPO is a pure RL framework using a token-wise action router to switch between discrete token generation and latent reasoning in LLMs, with joint optimization showing outperformance on benchmarks.
-
Medical Reasoning with Large Language Models: A Survey and MR-Bench
LLMs show strong exam performance on medical tasks but exhibit a clear gap in accuracy on authentic clinical decision-making as measured by the new MR-Bench benchmark and unified evaluations.
-
Reinforced Preference Optimization for Reasoning-Augmented Recommendations
RPORec unifies LLM reasoning with a recommendation head through reasoning-augmented modeling and reinforced preference optimization to improve recommendation accuracy and interpretability.
-
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.