BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
sigir26-009 · Full research paper · Weiqin Yang, Bohao Wang, Zhenxiang Xu, Jiawei Chen, Shengjia Zhang, Jingbang Chen, Canghong Jin, Can Wang
Knowledge Infusion and Open-World Au · 50% Preference Alignment and Optimizatio · 25% Generative Recommendation and Item T · 25%
Abstract
Recent years have seen a rapid surge in research leveraging Large Language Models (LLMs) for recommendation. These methods typically employ supervised fine-tuning (SFT) to adapt LLMs to recommendation scenarios, and utilize beam search during inference to efficiently retrieve B top-ranked recommended items. However, we identify a critical training-inference inconsistency: while SFT optimizes the overall probability of positive items, it does not guarantee that such items will be retrieved by beam search even if they possess high overall probabilities. Due to the greedy pruning mechanism, beam search can prematurely discard a positive item once its prefix probability is insufficient.
Assigned reviewers
| # | Reviewer | Match | Why (closest evidence publications in the taxonomy) | |
|---|---|---|---|---|
| 1 | Shuchang Liu 0001 | 51 | 87 DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems (2025) Preference Alignment and Optimization 87 Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5) (2022) Knowledge Infusion and Open-World Augmentation 50 Comprehensive List Generation for Multi-Generator Reranking (2025) Recommendation with Search and Ranking |
|
| 2 | Keqin Bao | 51 | 64 Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models (2024) Generative Recommendation and Item Tokenization 64 A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems (2025) Generative Recommendation and Item Tokenization 62 TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation (2023) Preference Alignment and Optimization |
Area chair
| Area chair | Match | |
|---|---|---|
| Pengyue Jia | 48 |
Area-chair candidates (5)
| Pengyue Jia assigned | 48 | 10 papers | |
| Maolin Wang 0001 | 47 | 15 papers | |
| Leyu Lin | 47 | 15 papers | |
| Yanan Niu | 46 | 15 papers | |
| Kun Gai | 46 | 5 papers |
Candidates from the panel ranked by match score
| # | Reviewer | Match | Load | Why | |
|---|---|---|---|---|---|
| 1 | Zhengyi Yang 0007 COI: co-author | 66 | 3 | 64 A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems (2025) Generative Recommendation and Item Tokenization 62 On Softmax Direct Preference Optimization for Recommendation (2024) Preference Alignment and Optimization |
|
| 2 | Jizhi Zhang COI: co-author | 61 | 3 | 64 Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models (2024) Generative Recommendation and Item Tokenization 62 TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation (2023) Preference Alignment and Optimization |
|
| 3 | Chongming Gao COI: co-author | 61 | 3 | 74 DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems (2025) Preference Alignment and Optimization 74 MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedback (2026) Preference Alignment and Optimization |
|
| 4 | Yang Zhang 0072 COI: co-author | 61 | 3 | 64 Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models (2024) Generative Recommendation and Item Tokenization 64 A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems (2025) Generative Recommendation and Item Tokenization |
|
| 5 | Jiancan Wu COI: co-author | 57 | 3 | 62 AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization (2025) Preference Alignment and Optimization 62 Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization (2025) Preference Alignment and Optimization |
|
| 6 | Bo Chen 0023 | 57 | 3 | 80 Large language models make sample-efficient recommender systems (2025) Efficiency and Deployment 80 How Can Recommender Systems Benefit from Large Language Models: A Survey (2025) Efficiency and Deployment |
|
| 7 | Jieming Zhu | 55 | 3 | 79 Efficient and Deployable Knowledge Infusion for Open-World Recommendations via Large Language Models (2026) Knowledge Infusion and Open-World Augmentation 77 Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models (2024) Knowledge Infusion and Open-World Augmentation |
|
| 8 | Bowen Zheng 0005 | 54 | 3 | 59 Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation (2024) Generative Recommendation and Item Tokenization 56 Autonomous Reasoning-Retrieval for Large Language Model Based Recommendation (2025) Reasoning-Intensive Retrieval and Ranking |
|
| 9 | Xuanhua Yang | 52 | 3 | 80 Breaking the Relevance-Diversity Seesaw: Hierarchical LLM Reasoning with RL for Industrial Novelty Recommendation (2026) Preference Alignment and Optimization 64 GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation (2026) Generative Retrieval and Ranking |
|
| 10 | Shuchang Liu 0001 assigned | 51 | 3 | 87 DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems (2025) Preference Alignment and Optimization 87 Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5) (2022) Knowledge Infusion and Open-World Augmentation |
|
| 11 | Keqin Bao assigned | 51 | 3 | 64 Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models (2024) Generative Recommendation and Item Tokenization 64 A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems (2025) Generative Recommendation and Item Tokenization |
|
| 12 | Yupeng Hou | 50 | 3 | 67 Large Language Models are Zero-Shot Rankers for Recommender Systems (2024) Efficiency and Deployment 54 Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation (2024) Collaborative-Semantic Representation Alignment |
|
| 13 | Junwei Pan | 49 | 3 | 69 Cross-Scale Collaboration between LLMs and Lightweight Sequential Recommenders with Domain-Specific Latent Reasoning (2026) Generative Recommendation and Item Tokenization 63 Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs (2025) Generative Recommendation and Item Tokenization |
|
| 14 | Jianling Wang | 49 | 3 | 67 Fresh Content Recommendation at Scale: A Multi-funnel Solution and the Potential of LLMs (2024) Efficiency and Deployment 54 LLMs for User Interest Exploration in Large-scale Recommendation Systems (2024) Sequential and Session-based Recommendation |
|
| 15 | Ed H. Chi | 49 | 3 | 61 PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations (2026) Item Tokenization and Semantic IDs 58 LLMs for User Interest Exploration in Large-scale Recommendation Systems (2024) Generative Recommendation and Item Tokenization |
|
| 16 | Qijiong Liu | 49 | 3 | 73 RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation (2025) Generative Retrieval and Recommendation Architectures 65 ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models (2024) LLM-Derived Knowledge Infusion |
|
| 17 | Huifeng Guo | 49 | 3 | 65 LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations (2025) Generative Recommendation and Item Tokenization 55 SELF: Surrogate-light Feature Selection with Large Language Models in Deep Recommender Systems (2025) LLM-Derived Knowledge Infusion |
|
| 18 | Yongqi Li 0001 | 48 | 3 | 69 Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation (2024) Generative Recommendation and Item Tokenization 64 Data-efficient Fine-tuning for LLM-based Recommendation (2024) Efficiency and Deployment |
|
| 19 | Hao Liu 0078 | 48 | 3 | 55 WeaveRec: An LLM-Based Cross-Domain Sequential Recommendation Framework with Model Merging (2026) Efficiency and Deployment 48 Mitigating Distribution Shifts in Sequential Recommendation: An Invariance Perspective (2025) Contrastive and Self-Supervised Sequential Recommendation |
|
| 20 | Xiao Zhang 0034 | 48 | 3 | 67 Large Language Models Enhanced Collaborative Filtering (2024) Preference Alignment and Optimization 54 Similarity = Value? Consultation Value-Assessment and Alignment for Personalized Search (2025) Personalized and Context-Aware Retrieval |
|
| 21 | Lichan Hong | 48 | 3 | 60 PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations (2026) Generative Recommendation and Item Tokenization 48 Recommender Systems with Generative Retrieval (2023) Item Tokenization and Semantic IDs |
|
| 22 | Han Li 0005 | 48 | 3 | 54 Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation (2025) Sequential and Session-based Recommendation 50 OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion (2026) Recommendation with Search and Ranking |
|
| 24 | Lantao Hu | 47 | 3 | 50 Comprehensive List Generation for Multi-Generator Reranking (2025) Recommendation with Search and Ranking 50 Unsupervised Ranking Ensemble Model for Recommendation (2024) Recommendation with Search and Ranking |
|
| 25 | Junjie Zhang 0009 | 47 | 3 | 56 STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning (2025) RL Training of Search Agents 54 Tapping the Potential of Large Language Models as Recommender Systems: A Comprehensive Framework and Empirical Analysis (2025) Efficiency and Deployment |
|
| 26 | Wei Guo 0006 | 47 | 3 | 67 Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation (2025) Efficiency and Deployment 50 Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model (2025) Generative Retrieval and Ranking |
|
| 27 | Bo Peng 0009 | 47 | 3 | 54 eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data (2024) Efficiency and Deployment 51 M2: Mixed Models With Preferences, Popularities and Transitions for Next-Basket Recommendation (2023) Efficient and Long-Sequence Sequential Recommendation |
|
| 29 | Jiangxia Cao | 47 | 3 | 54 Enhancing Content-based Recommendation via Large Language Model (2024) Collaborative-Semantic Representation Alignment 49 CDSRNP: Cross-Domain Sequential Recommendation via Neural Process (2025) Cross-Domain Sequential Recommendation |
|
| 30 | Min Hou 0004 | 47 | 3 | 64 RecCocktail: A Generalizable and Efficient Framework for LLM-Based Recommendation (2026) Preference Alignment and Optimization 55 WeaveRec: An LLM-Based Cross-Domain Sequential Recommendation Framework with Model Merging (2026) Efficiency and Deployment |
|
| 32 | Yongxin Ni | 46 | 3 | 49 Bridging NIP and MLM: A Unified Meta-Learning Framework for Sequential Recommendation (2026) Meta-Learning for Cold-Start Recommendation 49 An Image Dataset for Benchmarking Recommender Systems with Raw Pixels (2024) Recommendation Systems and Evaluation |
|
| 33 | Yang Song 0008 | 46 | 3 | 51 Large Language Models Enhanced Collaborative Filtering (2024) LLM-Enhanced Collaborative Filtering 49 Mixed Attention Network for Cross-domain Sequential Recommendation (2024) Cross-Domain and Cross-Market Sequential Recommendation |