Retrieval coverage limits LLM rerankers in cold-start recommendation; a learned hybrid fusion improves pool quality but LLM reranking often degrades end-to-end performance while simpler rankers exploit the pool.
hub
In: Proceedings of the 16th ACM Conference on Recommender Systems
12 Pith papers cite this work, alongside 426 external citations. Polarity classification is still indexing.
12
Pith papers citing it
426
external citations · external index
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 12roles
background 1polarities
background 1representative citing papers
Quotient DAGs enable forward-flow importance sampling and exact unordered slate propensities via Forward-DP for autoregressive slate loggers under set-sufficient interfaces.
Exact LTI Koopman models for nonlinear control systems require affine linear dynamics under controllability and coordinate inclusion assumptions.
AI brand mentions in ChatGPT/Claude/Gemini conversations causally raise open-web searches and visits by 4.3/2.4/1.0pp via pre-trend event study, stance classifier, and same-category controls on joined clickstream-conversation panel data.
DREAM proposes intent-aware tokenization, frozen-model evaluation, and dynamic beams to refine early SID assignments and improve cold-start performance in generative recommenders on Amazon benchmarks.
A survey that organizes fairness research in LLM-based recommender systems via a two-dimensional taxonomy of bias mechanisms and fairness targets while linking to other trustworthy AI concerns.
A Llama-based model trained on serialized user stories unifies item, carousel, and search ranking and outperforms specialist baselines offline while improving some online metrics and reducing latency.
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.
GPlan compresses LLM reasoning into small models via Progressive Implicit CoT Distillation and Spatiotemporal Counterfactual DPO to generate logically coherent and physically executable intent sequences for recommendation.
A tuning-free LLM pipeline that annotates user histories with inferred motives and uses a reflection loop to correct search queries beats ID-based recommenders on a sparse industrial risk dataset.
Heuristic demonstration selection methods outperform embedding-based methods for practical LLM-based next POI prediction on three real-world datasets.
SAILRec uses dual-side semantic alignment and hierarchical attention steering to improve how LLMs incorporate collaborative embeddings for recommendations, outperforming baselines on MovieLens-1M and Amazon-Book datasets.
citing papers explorer
-
Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation
Retrieval coverage limits LLM rerankers in cold-start recommendation; a learned hybrid fusion improves pool quality but LLM reranking often degrades end-to-end performance while simpler rankers exploit the pool.
-
Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities
Quotient DAGs enable forward-flow importance sampling and exact unordered slate propensities via Forward-DP for autoregressive slate loggers under set-sufficient interfaces.
-
Limitations of LTI Koopman Modeling for Nonlinear Control Systems
Exact LTI Koopman models for nonlinear control systems require affine linear dynamics under controllability and coordinate inclusion assumptions.
-
From Prompt to Purchase: How AI Brand Recommendations Move Consumers on the Open Web
AI brand mentions in ChatGPT/Claude/Gemini conversations causally raise open-web searches and visits by 4.3/2.4/1.0pp via pre-trend event study, stance classifier, and same-category controls on joined clickstream-conversation panel data.
-
DREAM: Dynamic Refinement of Early Assignment Mappings
DREAM proposes intent-aware tokenization, frozen-model evaluation, and dynamic beams to refine early SID assignments and improve cold-start performance in generative recommenders on Amazon benchmarks.
-
Rethinking Fairness in LLM-Based Recommender Systems: A Survey
A survey that organizes fairness research in LLM-based recommender systems via a two-dimensional taxonomy of bias mechanisms and fairness targets while linking to other trustworthy AI concerns.
-
TubiFM: Unified Item, Carousel, and Search Ranking for Streaming Discovery
A Llama-based model trained on serialized user stories unifies item, carousel, and search ranking and outperforms specialist baselines offline while improving some online metrics and reducing latency.
-
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.
-
Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap
GPlan compresses LLM reasoning into small models via Progressive Implicit CoT Distillation and Spatiotemporal Counterfactual DPO to generate logically coherent and physically executable intent sequences for recommendation.
-
LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains
A tuning-free LLM pipeline that annotates user histories with inferred motives and uses a reflection loop to correct search queries beats ID-based recommenders on a sparse industrial risk dataset.
-
A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Prediction
Heuristic demonstration selection methods outperform embedding-based methods for practical LLM-based next POI prediction on three real-world datasets.
-
SAILRec: Steering LLM Attention to Dual-Side Semantically Aligned Collaborative Embeddings for Recommendation
SAILRec uses dual-side semantic alignment and hierarchical attention steering to improve how LLMs incorporate collaborative embeddings for recommendations, outperforming baselines on MovieLens-1M and Amazon-Book datasets.