A Unified Language Model for Large Scale Search, Recommendation, and Reasoning

Marco De Nadai; Edoardo D'Amico; Max Lefarov; Alexandre Tamborrino; Divita Vohra; Mark VanMiddlesworth; Shawn Lin; Jacqueline Wood

cs.IRMar 18, 2026

A Unified Language Model for Large Scale Search, Recommendation, and Reasoning

Authors: Marco De Nadai, Edoardo D'Amico, Max Lefarov, Alexandre Tamborrino, Divita Vohra, Mark VanMiddlesworth, Shawn Lin, Jacqueline Wood,

Organizations: Spotify Denmark, Spain, Germany, France, United States, United Kingdom

Abstract

LLMs are increasingly applied to recommendation, retrieval, and reasoning, yet deploying a single end-to-end model that can jointly support these behaviors over large, heterogeneous catalogs remains challenging. Such systems must generate unambiguous references to real items, handle multiple entity types, and operate under strict latency and reliability constraints requirements that are difficult to satisfy with text-only generation. While tool-augmented recommender systems address parts of this problem, they introduce orchestration complexity and limit end-to-end optimization. We view this setting as an instance of a broader research problem: how to adapt LLMs to reason jointly over multiple-domain entities, users, and language in a fully self-contained manner. To this end, we introduce NEO, a framework that adapts a pre-trained decoder-only LLM into a tool-free, catalog-grounded generator. NEO represents items as SIDs and trains a single model to interleave natural language and typed item identifiers within a shared sequence. Text prompts control the task, target entity type, and output format (IDs, text, or mixed), while constrained decoding guarantees catalog-valid item generation without restricting free-form text. We refer to this instruction-conditioned controllability as language-steerability. We treat SIDs as a distinct modality and study design choices for integrating discrete entity representations into LLMs via staged alignment and instruction tuning. We evaluate NEO at scale on a real-world catalog of over 10M items across multiple media types and discovery tasks, including recommendation, search, and user understanding. In offline experiments, NEO consistently outperforms strong task-specific baselines and exhibits cross-task transfer, demonstrating a practical path toward consolidating large-scale discovery capabilities into a single language-steerable generative model.

Figures & tables

Figure 1. NEO adapts pre-trained LLMs to speak multi-item-type catalogs (e.g. audiobooks and podcasts) through SIDs (e.g. 2 tokens long tuples), and to output both text and SIDs.

Capability $\downarrow$ / System $\rightarrow$	Generative SID Retrieval ( Qu et al., 2024 ; Rajput et al., 2024 )	Tool-based LLMs ( Doh et al., 2025a ; Friedman et al., 2023 ; Lyu et al., 2024 ; Wang et al., 2024d )	PLUM ( He et al., 2025 )	TalkPlay ( Doh et al., 2025b )	NEO (this work)
Discrete item pointers	✓	✗	✓	✓	✓
Mixed text + item output	✗	$\blacktriangle$	✗	✓	✓
Mixed text + item input	$\blacktriangle$	✓	✓	✓	✓
User behaviour in input	✓	$\blacktriangle$	✓	$\blacktriangle$	✓
Language-steerable behavior	✗	✓	$\blacktriangle$	✓	✓
Multiple item types	$\blacktriangle$	$\blacktriangle$	✗	✗	✓

Table 1. Comparison of NEO with prior recommendation paradigms. While several approaches support individual capabilities (e.g., discrete item IDs or LLM-based generation), NEO is the first to combine typed item addressing, mixed text–item outputs, language-steerable behavior, and multi-task discovery within a single tool-calling-free generative model.

Figure 2. We illustrate our approach as the first three stages in a more general four-stage pipeline. In the general case, in Stage 1, semantic representations are learned—such as semantic IDs (SIDs)—to capture entities, their structure, and relationships. In Stage 2, domain grounding is performed via one or both of (i) adaptation over user-behavior sequences and (ii) domain alignment between SID/text pairs, to learn a shared latent space between entities and natural language. This enables the model to use text and SIDs interchangeably and to learn sequential, domain-relevant concepts. Stage 3 teaches the model to answer questions, follow commands, and generate grounded outputs through multi-task instruction-following. We prioritize diversity of tasks over depth within any single task. In Stage 4, we may leverage task-specific datasets and objectives related to the targeted use case (e.g., topic discovery and business constraints) via task-specific fine-tuning, reinforcement learning, and related techniques. We indicate typical choices for which parameters are kept frozen (ice) or trainable (fire) for each stage.

Semantic IDs
Method	$\Delta$ HR@10
NEO (Baseline)	-
A - Atomic item IDs	-59.7%
B - LSH quantizer	-51.2%
C - No augmented data	-2.9%
D - Collaborative filtering	-25.6%

Table 2. Ablation for multiple types of item representation.

Inference strategy	$\Delta$ HR@K		$\Delta$ latency
Inference strategy	$k=10$	$k=30$	$k=10$
NEO (Baseline)	-	-	-
A - Beam Search w/o constrains	-1.80%	-1.93%	-2.92%
B - Top- $p$ sampling	-21.97%	-32.41%	-7.91%

Table 3. Accuracy/latency trade-off at inference time.

Method	HR@K $\uparrow$		NDCG@K $\uparrow$
Method	$k=10$	$k=30$	$k=10$	$k=30$
NEO (Baseline)	-	-	-	-
A - w/o Domain Grounding	${\color[rgb]{0.6992,0.1328,0.1328}-6\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-7\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-8\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-8\%}$
B - Everything in two-stages	${\color[rgb]{0.6992,0.1328,0.1328}-8\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-7\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-10\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-10\%}$
C - Random init	${\color[rgb]{0.6992,0.1328,0.1328}-44\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-44\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-44\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-43\%}$
D - Continuos pretraining	${\color[rgb]{0.6992,0.1328,0.1328}-3\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-3\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-2\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-3\%}$

Table 4. Comparison of training strategies alternative to NEO.

Episode Recommendation
Method	HR@K $\uparrow$		NDCG@K $\uparrow$
Method	$k=10$	$k=30$	$k=10$	$k=30$
Baseline	-	-	-	-
NEO - mono	${\color[rgb]{0.1328,0.5469,0.1328}+57\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+41\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+80\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+60\%}$
NEO - multi	${\color[rgb]{0.1328,0.5469,0.1328}+58\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+40\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+80\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+59\%}$
Show Recommendations

Table 5. Multi-task performance

Variation		Artists	Episodes
Interest profiling	Coverage	3.79	3.47
Interest profiling	Groundedness	3.81	3.50
Recsplanation	Faithfulness item	4.08	3.28
	Faithfulness history	4.16	2.79
	Deceptiveness	4.74	4.52

Table 6. LLM as a Judge result for user analysis and recsplanation tasks. Scores from 0 to 5

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 3 — Figure 3. Recsplanation result for an episode request. This randomly selected result shows that the model can interleave recommendations (SIDs) and explanation (text) fluently.

Panel of Figure 4 — Figure 4. Qualitative example of user understanding for an episode, from the SID history of an user.

Hyperparameters	Stage 2	Stage 3
Learning rate	$1.0\times 10^{-3}$	$1\times 10^{-4}$
LR scheduler	Cosine	Cosine
Weight decay	$0.01$	$0.01$
Gradient clip	$1.0$	$1.0$
Optimizer	AdamW ( $\beta_{1}=0.9,\beta_{2}=0.95$ )
Warm-up steps	$300$	$400$

Appendix

Table 7. Detailed hyperparameters of NEO applied to Qwen

User type	HR@K $\uparrow$		NDCG@K $\uparrow$
User type	$k=10$	$k=30$	$k=10$	$k=30$
Coldstart	${\color[rgb]{0.6992,0.1328,0.1328}-48\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-57\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-34\%}$	${\color[rgb]{0.6992,0.1328,0.1328}-40\%}$
Warmstart	${\color[rgb]{0.1328,0.5469,0.1328}+57\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+40\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+70\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+60\%}$

Appendix

Table 8. Episode recommendations detailed results. The LLM has room for improvement in coldstart users, which represent

\sim

2% of our data.

Item type
Variation	HR@K $\uparrow$		NDCG@K $\uparrow$
Variation	$k=10$	$k=30$	$k=10$	$k=30$
Artists	${\color[rgb]{0.1328,0.5469,0.1328}+36\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+35\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+38\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+38\%}$
Audiobooks	${\color[rgb]{0.1328,0.5469,0.1328}+26\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+27\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+29\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+30\%}$
Episodes	${\color[rgb]{0.1328,0.5469,0.1328}+40\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+16\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+73\%}$	${\color[rgb]{0.1328,0.5469,0.1328}+59\%}$
Query complexity

Appendix

Table 9. Text-based retrieval/search performance by item type and query complexity.

Panel of Figure 5 — Figure 5. Prompt template used for LLM as a Judge for the user analysis task.

Panel of Figure 6 — Figure 6. Prompt template used for LLM as a Judge for the recsplanation task.

Panel of Figure 7 — Figure 7. Prompt template used for text-based retrieval/search.

Panel of Figure 8 — Figure 8. Prompt template used for episode recommendation.

Panel of Figure 9 — Figure 9. Prompt template used for show recommendation.

Panel of Figure 10 — Figure 10. Prompt template used for audiobook recommendation.

Large Language Model-Based Recommendation

Large language model-based recommendation uses language models to personalize ranking, retrieval, and conversational suggestions from text and behavior.

See all 210 papers

Aligning Large Language Models with Searcher Preferences
Mar 11, 2026Wei Wu, Peilun Zhou, Liyi Chen +6Personalized Language Model Alignment Generative Retrieval
School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China · Xiaohongshu Inc., Beijing, China · Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China +1
GEM: A Generative Embedding Model Bridging Reasoning and Retrieval
Aug 13, 2026Zhili Shen, Craig MacdonaldText Embedding Models
University of Glasgow
Reasoning over Semantic IDs Enhances Generative Recommendation
Mar 24, 2026Yingzhi He, Yan Sun, Junfei Tan +6Large Language Model-Based Recommendation Generative Recommendation
National University of Singapore Singapore, Singapore · University of Science and Technology of China Hefei, China · Tencent Inc. Shenzhen, China

Mar 11, 2026J/K move · Enter open · S save

Aligning Large Language Models with Searcher Preferences

Wei Wu, Peilun Zhou, Liyi Chen, Qimeng Wang+5

School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China · Xiaohongshu Inc., Beijing, China · Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China+1

Personalized Language Model Alignment Generative Retrieval

Open paper AskPDF arXiv

The paradigm shift from item-centric ranking to answer-centric synthesis is redefining the role of search engines. While recent industrial progress has applied generative techniques to closed-set item ranking in e-commerce, research and deployment of open-ended generative search on large content platforms remain limited. This setting introduces challenges, including robustness to noisy retrieval, non-negotiable safety guarantees, and alignment with diverse user needs. In this work, we introduce SearchLLM, the first large language model (LLM) for open-ended generative search. We design a hierarchical, multi-dimensional reward system that separates bottom-line constraints, including factual grounding, basic answer quality and format compliance, from behavior optimization objectives that promote robustness to noisy retrieval and alignment with user needs. Concretely, our reward model evaluates responses conditioned on the user query, session history, and retrieved evidence set, combining rule-based checks with human-calibrated LLM judges to produce an interpretable score vector over these dimensions. We introduce a Gated Aggregation Strategy to derive the training reward for optimizing SearchLLM with Group Relative Policy Optimization (GRPO). We deploy SearchLLM in the AI search entry of RedNote. Offline evaluations and online A/B tests show improved generation quality and user engagement, increasing Valid Consumption Rate by 1.03% and reducing Re-search Rate by 2.81%, while upholding strict safety and reliability standards.

Abstract

Large Language Model-Based Recommendation

Explore similar work

Aligning Large Language Models with Searcher Preferences

GEM: A Generative Embedding Model Bridging Reasoning and Retrieval

Reasoning over Semantic IDs Enhances Generative Recommendation