REVIEW 14 cited by
LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Graph recommendation methods, representing a connected interaction perspective, reformulate user-item interactions as graphs to leverage graph structure and topology to recommend and have proved practical effectiveness at scale. Large language models, representing a textual generative perspective, excel at modeling user languages, understanding behavioral contexts, capturing user-item semantic relationships, analyzing textual sentiments, and generating coherent and contextually relevant texts as recommendations. However, there is a gap between the connected graph perspective and the text generation perspective as the task formulations are different. A research question arises: how can we effectively integrate the two perspectives for more personalized recsys? To fill this gap, we propose to incorporate graph-edge information into LLMs via prompt and attention innovations. We reformulate recommendations as a probabilistic generative problem using prompts. We develop a framework to incorporate graph edge information from the prompt and attention mechanisms for graph-structured LLM recommendations. We develop a new prompt design that brings in both first-order and second-order graph relationships; we devise an improved LLM attention mechanism to embed direct the spatial and connectivity information of edges. Our evaluation of real-world datasets demonstrates the framework's ability to understand connectivity information in graph data and to improve the relevance and quality of recommendation results.
Forward citations
Cited by 14 Pith papers
-
PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models
A multi-grained reward framework fine-tunes an LLM with PPO to generate whole-page recommendations, showing that page-level and item-level reward heads are complementary.
-
Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback
Reinforcement learning fine-tuning with numerical fitness rewards improves equation discovery accuracy and noise robustness of a pretrained symbolic regression transformer.
-
Brownian Bridge Augmented Surrogate Simulation and Injection Planning for Geological CO$_2$ Storage
A Brownian bridge augmented framework improves surrogate simulation accuracy and injection plan quality on synthetic CO2 storage datasets compared with established baselines.
-
Multi-agents based User Values Mining for Recommendation
A multi-LLM debate framework extracts Schwartz value labels from user interaction histories, and adding these labels through contrastive learning improves recommendation accuracy on PENS and MovieLens-1M.
-
SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation
An LLM-based user simulator with persona matching, memory, and visual perception aligns more closely with real users than earlier agent models and can support offline A/B testing for recommender systems.
-
Integrating LLM-Derived Multi-Semantic Intent into Graph Model for Session-based Recommendation
A session-based recommender that uses a large language model to infer multiple user intents from a GNN-selected candidate set and aligns them with the GNN's structural representation, improving ranking metrics on Beau...
-
Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives
TimesCLIP aligns image-based and text-based views of the same time series via contrastive learning to improve forecasting accuracy on several benchmarks, but the full multimodal model is not used on two of the six lon...
-
Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming
A generator-critic pair of LLM agents creates new tabular features from feature names, data summaries, and task descriptions, and is reported to improve Random Forest accuracy more than supervised feature engineering ...
-
MixLLM: Dynamic Routing in Mixed Large Language Models
MixLLM routes each query to a cost-effective LLM by combining tag-enhanced embeddings, per-model quality and cost predictors, a latency penalty, and online bandit feedback.
-
LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation
A product-of-experts decoder that blends a fine-tuned LLM's token probabilities with a gradient-searched sequence decoder produces more valid and stable feature transformations than either alone.
-
Graph Foundation Models for Recommendation: A Comprehensive Survey
A comprehensive survey that categorizes graph foundation model approaches to recommendation into graph-augmented LLM, LLM-augmented graph, and LLM-graph harmonization.
-
Topic-Aware Knowledge Graph with Large Language Models for Interoperability in Recommender Systems
An LLM-based pipeline extracts subtype and keyword topics from side and context information, adds them to a standardized knowledge graph, and reports improved PGPR recommendation metrics on two Amazon datasets.
-
Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenization
A recommender system that converts item IDs into shared code tokens and fine-tunes Llama with alignment tasks plus negative sampling beats LC-Rec on three Amazon datasets by a few percent.
-
When Transformers Meet Recommenders: Integrating Self-Attentive Sequential Recommendation with Fine-Tuned LLMs
SASRecLLM, a hybrid of SASRec and a LoRA-fine-tuned LLM, reports modest gains over TALLRec on MovieLens but shows inconsistent and contradictory results on Amazon and in warm-start settings.
Discussion (0). Continue with ORCID to comment.