Pith. sign in

REVIEW 14 cited by

Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2203.13366 v7 pith:WGVBFZ4J submitted 2022-03-24 cs.IR cs.AIcs.CLcs.LG

Shijie Geng , Shuchang Liu , Zuohui Fu , Yingqiang Ge , Yongfeng Zhang This is my paper · ORCID
classification cs.IRcs.AIcs.CLcs.LG
keywords recommendationlanguagemodeltasksdifferentparadigmpersonalizedprompt
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

For a long time, different recommendation tasks typically require designing task-specific architectures and training objectives. As a result, it is hard to transfer the learned knowledge and representations from one task to another, thus restricting the generalization ability of existing recommendation approaches, e.g., a sequential recommendation model can hardly be applied or transferred to a review generation method. To deal with such issues, considering that language can describe almost anything and language grounding is a powerful medium to represent various problems or tasks, we present a flexible and unified text-to-text paradigm called "Pretrain, Personalized Prompt, and Predict Paradigm" (P5) for recommendation, which unifies various recommendation tasks in a shared framework. In P5, all data such as user-item interactions, user descriptions, item metadata, and user reviews are converted to a common format -- natural language sequences. The rich information from natural language assists P5 to capture deeper semantics for personalization and recommendation. Specifically, P5 learns different tasks with the same language modeling objective during pretraining. Thus, it serves as the foundation model for various downstream recommendation tasks, allows easy integration with other modalities, and enables instruction-based recommendation based on prompts. P5 advances recommender systems from shallow model to deep model to big model, and will revolutionize the technical form of recommender systems towards universal recommendation engine. With adaptive personalized prompt for different users, P5 is able to make predictions in a zero-shot or few-shot manner and largely reduces the necessity for extensive fine-tuning. On several recommendation benchmarks, we conduct experiments to show the effectiveness of P5. We release the source code at https://github.com/jeykigung/P5.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. HCGRec: Hint-Conditioned Generative Recommendation with Semantic IDs

    cs.IR 2026-08 conditional novelty 6.0 of 10

    HCGRec supplies the shortest target-prefix hint for hard training instances during GRPO post-training, then optimizes only the unhinted suffix, reducing zero-advantage rollout groups and improving sequential recommend...

  2. Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging

    cs.IR 2026-08 conditional novelty 6.0 of 10

    REAM merges slow- and fast-thinking recommender models at the per-attention-head level, cutting reasoning length by up to 24.3% while preserving rating accuracy.

  3. Bridging the Information Gap: Semantic Densification and Hindsight Distillation for Cold-Start Prediction

    cs.AI 2026-07 conditional novelty 6.0 of 10

    SemRaD improves cold-start LTV and CVR prediction by encoding LLM-written semantic profiles with a learned gate and distilling a hindsight-reconciled future target through per-user distillation experts, confirmed by a...

  4. An LLM-powered Agentic Recommendation System for Connected TV Content Discovery

    cs.IR 2026-07 conditional novelty 6.0 of 10

    A hybrid system where an LLM agent generates CTV topic channels and traditional ML ranks the media inside them is engineered to run at production latency via async caching, but only its retrieval component is quality-...

  5. LLM-Based User Personas for Recommendations at Scale

    cs.IR 2026-06 unverdicted novelty 6.0 of 10

    A framework for real-time LLM-based user interest personas in large-scale video recommendations, using distillation, async inference, and video clustering to balance interests with novel topics and improve viewer valu...

  6. Efficient Item ID Generation for Large-Scale LLM-based Recommendation

    cs.IR 2025-09 conditional novelty 6.0 of 10

    LLM-based recommenders can treat item IDs as single direct embeddings and decode in one step, with a two-level softmax for efficiency and quality matching or beating multi-token models.

  7. ELIXIR: Efficient and LIghtweight model for eXplaIning Recommendations

    cs.IR 2025-08 conditional novelty 6.0 of 10

    ELIXIR combines aspect-aware user and item representations with prompt tuning on a frozen 60M-parameter T5 to generate personalized reviews, outperforming GPT-2-based baselines on TripAdvisor and RateBeer.

  8. LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models

    cs.IR 2025-07 conditional novelty 6.0 of 10

    An LLM-driven agent generates synthetic interaction sequences that, when queried against a target sequential recommender, produce surrogate models with higher agreement to the target than random or autoregressive data...

  9. X-Cross: Dynamic Integration of Language Models for Cross-Domain Sequential Recommendation

    cs.IR 2025-04 conditional novelty 6.0 of 10

    X-Cross recombines frozen LoRA-tuned language-model activations layer by layer and reaches LoRA-comparable or better cross-domain recommendation accuracy with 25 percent of the new parameters and 50-75 percent less data.

  10. Benchmark Leakage Trap: Can We Trust LLM-based Recommendation?

    cs.LG 2026-02 conditional novelty 5.0 of 10

    Fine-tuning an LLM recommender on a slice of the benchmark inflates AUC/UAUC for in-domain leakage and degrades it for out-of-domain leakage, showing benchmark contamination can distort LLM-based recommendation evaluation.

  11. RecCoT: Enhancing Recommendation via Chain-of-Thought

    cs.IR 2025-06 conditional novelty 5.0 of 10

    A slow-large, fast-small framework that generates chain-of-thought explanations from reviews and caches the resulting semantic embeddings improves Amazon rating prediction over several baselines.

  12. Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Models

    cs.IR 2024-12 conditional novelty 5.0 of 10

    RSLLM mixes item ID embeddings from classical recommenders with text titles inside an LLM prompt and uses two-stage contrastive fine-tuning to improve sequential recommendation.

  13. Instruction-Based Fine-tuning of Open-Source LLMs for Predicting Customer Purchase Behaviors

    cs.IR 2025-01 conditional novelty 4.0 of 10

    Instruction-tuned Mistral 7B achieves modestly higher F1 than CNN/LSTM on next merchant category prediction, but the evaluation lacks significance tests and the weighted F1 is dominated by an 'Other' class.

  14. From Interests to Insights: An LLM Approach to Course Recommendations Using Natural Language Queries

    cs.IR 2024-12 conditional novelty 4.0 of 10

    A two-stage LLM pipeline generates an idealized course description from a student query, retrieves similar courses by embedding, and returns ten ranked recommendations with rationales and confidence scores.

Pith tools