# Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View

arXiv: https://arxiv.org/abs/2505.03336 · HTML: https://mlsanity.com/paper/2505.03336/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 6 May 2025.

## Builds on (most cited first, 21 of 21)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [Learnable Item Tokenization for Generative Recommendation](https://mlsanity.com/paper/2405.07314/) (2024)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems](https://mlsanity.com/paper/2308.08434/) (2023)
- [Collaborative Large Language Model for Recommender Systems](https://mlsanity.com/paper/2311.01343/) (2023)
- [GenRec: Large Language Model for Generative Recommendation](https://mlsanity.com/paper/2307.00457/) (2023)
- [IDGenRec: LLM-RecSys Alignment with Textual ID Learning](https://mlsanity.com/paper/2403.19021/) (2024)
- [Order-agnostic Identifier for Large Language Model-based Generative Recommendation](https://mlsanity.com/paper/2502.10833/) (2025)
- [RecAI: Leveraging Large Language Models for Next-Generation Recommender Systems](https://mlsanity.com/paper/2403.06465/) (2024)
- [Aligning Large Language Models for Controllable Recommendations](https://mlsanity.com/paper/2403.05063/) (2024)
- [Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations](https://mlsanity.com/paper/2311.10779/) (2023)
- [On Explaining Recommendations with Large Language Models: A Review](https://mlsanity.com/paper/2411.19576/) (2024)

## Built on by (most cited first, 6 of 6)

- [Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators](https://mlsanity.com/paper/2602.22647/) (2026)
- [Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness](https://mlsanity.com/paper/2608.10008/) (2026)
- [Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models](https://mlsanity.com/paper/2511.05286/) (2025)
- [CRAMER: Control via Request-Aware Masking for Editing Recommenders](https://mlsanity.com/paper/2608.25370/) (2026)
- [ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use Agents](https://mlsanity.com/paper/2608.30685/) (2026)
- [Constraint-Aware Training](https://mlsanity.com/paper/2610.02909/) (2026)

## Abstract (arXiv)

Recommender systems based on Large Language Models (LLMs) are often plagued by hallucinations of out-of-domain (OOD) items. To address this, we propose RecLM, a unified framework that bridges the gap between retrieval and generation by instantiating three grounding paradigms under a single architecture: embedding-based retrieval, constrained generation over rewritten item titles, and discrete item-tokenizer generation. Using the same backbone LLM and prompts, we systematically compare these three views on public benchmarks. RecLM strictly eradicates OOD recommendations (OOD@10 = 0) across all variants, and the constrained generation variants RecLM-cgen and RecLM-token achieve overall state-of-the-art accuracy compared to both strong ID-based and LLM-based baselines. Our unified view provides a systematic basis for comparing three distinct paradigms to reduce item hallucinations, offering a practical framework to facilitate the application of LLMs to recommendation tasks. Source code is at https://github.com/microsoft/RecAI.