mlsanityData to 7 Oct 2026

Leveraging LLM Reasoning Enhances Personalized Recommender Systems

arXiv 2408.00802 ↗First posted 22 Jul 2024cs.IR cs.AI cs.CLcited by 26

On the map: LLM reasoning → LLM reasoning for recommendation

Abstract (arXiv)

Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and logical chains of thought, the application of LLM reasoning in recommendation systems (RecSys) presents a distinct challenge. RecSys tasks revolve around subjectivity and personalized preferences, an under-explored domain in utilizing LLMs' reasoning capabilities. Our study explores several aspects to better understand reasoning for RecSys and demonstrate how task quality improves by utilizing LLM reasoning in both zero-shot and finetuning settings. Additionally, we propose RecSAVER (Recommender Systems Automatic Verification and Evaluation of Reasoning) to automatically assess the quality of LLM reasoning responses without the requirement of curated gold references or human raters. We show that our framework aligns with real human judgment on the coherence and faithfulness of reasoning responses. Overall, our work shows that incorporating reasoning into RecSys can improve personalized tasks, paving the way for further advancements in recommender system methodologies.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 23 of its 34 references that are in the map. First posted on arXiv 22 Jul 2024.

Builds on

23 of 34 references.

References · 23

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  10. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  11. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  12. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
11 more
  1. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 396
  2. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  3. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 241
  4. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 175
  5. 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
  6. 2022M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systemscited by 152
  7. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 113
  8. 2022Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learningcited by 85
  9. 2022Iteratively Prompt Pre-trained Language Models for Chain of Thoughtcited by 75
  10. 2023Leveraging Large Language Models in Conversational Recommender Systemscited by 63
  11. 2023LLMRec: Benchmarking Large Language Models on Recommendation Taskcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 15; 2026: 9.

26 papers.

Sort:

By area:

  1. 2025OneRec-Think: In-Text Reasoning for Generative Recommendationcited by 47
  2. 2025Reinforced Latent Reasoning for LLM-based Recommendationcited by 46
  3. 2025Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendationcited by 21
  4. 2025R2ec: Towards Large Recommender Models with Reasoningcited by 13
  5. 2025PosterMate: Audience-driven Collaborative Persona Agents for Poster Designcited by 9
  6. 2024Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandemcited by 8
  7. 2024STAR: A Simple Training-free Approach for Recommendations using Large Language Modelscited by 8
  8. 2025CoMaPOI: A Collaborative Multi-Agent Framework for Next POI Prediction Bridging the Gap Between Trajectory and Languagecited by 8
  9. 2025Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendationcited by 7
  10. 2025Memory Assisted LLM for Personalized Recommendation Systemcited by 7
  11. 2025A Survey on Large Language Models in Multimodal Recommender Systemscited by 7
  12. 2025RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoningcited by 5
14 more
  1. 2025Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discoverycited by 3
  2. 2026ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuningcited by 3
  3. 2025HADSF: Aspect Aware Semantic Control for Explainable Recommendationcited by 2
  4. 2025Context-Aware Pragmatic Metacognitive Prompting for Sarcasm Detectioncited by 2
  5. 2026Verifiable Reasoning for LLM-based Generative Recommendationcited by 2
  6. 2025Music Recommendation with Large Language Models: Challenges, Opportunities, and Evaluationcited by 1
  7. 2026Enriching Semantic Profiles into Knowledge Graph for Recommender Systems Using Large Language Modelscited by 1
  8. 2026Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Targetcited by 1
  9. 2025From What to Why: Thought-Space Recommendation with Small Language Modelscited by 0
  10. 2026On Reasoning Behind Next Occupation Recommendationcited by 0
  11. 2026RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendationcited by 0
  12. 2026Bridging the Information Gap: Semantic Densification and Hindsight Distillation for Cold-Start Predictioncited by 0
  13. 2026FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUscited by 0
  14. 2026Profiling What Matters: Context-Aware Item Profiles from Large-Scale Metadata for LLM Recommenderscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning
  2. 2023Enhancing Recommender Systems with Large Language Model Reasoning Graphs
  3. 2025MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs
  4. 2026Reinforced Preference Optimization for Reasoning-Augmented Recommendations
  5. 2026LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing
  6. 2025Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation
  7. 2023Leveraging Large Language Models for Pre-trained Recommender Systems
  8. 2026SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendation