REVIEW 8 cited by
Language-Based User Profiles for Recommendation
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
read the original abstract
Most conventional recommendation methods (e.g., matrix factorization) represent user profiles as high-dimensional vectors. Unfortunately, these vectors lack interpretability and steerability, and often perform poorly in cold-start settings. To address these shortcomings, we explore the use of user profiles that are represented as human-readable text. We propose the Language-based Factorization Model (LFM), which is essentially an encoder/decoder model where both the encoder and the decoder are large language models (LLMs). The encoder LLM generates a compact natural-language profile of the user's interests from the user's rating history. The decoder LLM uses this summary profile to complete predictive downstream tasks. We evaluate our LFM approach on the MovieLens dataset, comparing it against matrix factorization and an LLM model that directly predicts from the user's rating history. In cold-start settings, we find that our method can have higher accuracy than matrix factorization. Furthermore, we find that generating a compact and human-readable summary often performs comparably with or better than direct LLM prediction, while enjoying better interpretability and shorter model input length. Our results motivate a number of future research directions and potential improvements.
Forward citations
Cited by 8 Pith papers
-
Biases in LLM-Generated Musical Taste Profiles for Recommendation
Users identify more with LLM-generated music taste profiles for some genres and user groups than others, and these biases differ across models.
-
Prediction Is Not Memory: Dual-Timescale Gated Profile Writing for Persistent User Modeling
A lightweight write-risk gate reduces harmful persistent-profile updates from 22.45% to about 14.5% on MicroLens-100K, and next-item ranking confidence is a poor substitute for write-risk scoring.
-
Bridging Textual Profiles and Latent User Embeddings for Personalization
BLUE aligns LLM-generated textual user profiles with embedding-based recommendation objectives via reinforcement learning and next-item text supervision, yielding better zero-shot performance and cross-domain transfer...
-
Federated User Behavior Modeling for Privacy-Preserving LLM Recommendation
SF-UBM enables privacy-preserving cross-domain LLM recommendation by federating semantic item representations, distilling domain knowledge, and aligning preferences into LLM soft prompts.
-
Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation
For cost-efficient LLMs, rephrasing, step-back, and structured reasoning prompts raise ranking accuracy; for high-performance LLMs, a simple baseline prompt matches complex prompts at a fraction of the cost.
-
LLM-Based Re-Ranking for Real Estate Search
An LLM pointwise re-ranker using user profiles and candidate-set statistics improved ranking quality in a real-estate marketplace, with statistically significant production gains of +5.3% CTR and +4.8% scheduled visits.
-
POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
POPI distills user preferences into reusable natural-language summaries via a shared inference model and conditions a generator on them, trained jointly with RL to improve personalization quality while cutting context...
-
Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluation
A review and position paper proposing a six-dimension success framework and risk diagnostics for evaluating LLM-based music recommendation systems.
Discussion (0). Sign in to comment.