CHIANGEL/Awesome-LLM-for-RecSys

MIT AI & ML low-activity

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

1.5k stars

88 forks

slow

GitHub +2 / week

awesome large-language-models llm llm4rec llm4rs recommender-systems recsys rs

1.5k

Stars

Forks

Open issues

Contributors

AI Analysis

A curated survey and resource collection documenting papers and research on the intersection of large language models and recommender systems. This is a research-focused curation project, best suited for academics, ML researchers, and practitioners actively working on LLM-enhanced recommendation systems—not for general-purpose software development or end-user applications. It serves the niche but growing subfield of LLM4RecSys by organizing and tracking published research.

AI & ML Research Project Discovery value: 5/10

Documentation 8/10

Activity 4/10

Community 7/10

Code quality 5/10

Inferred from signals mentioned in the README (tests, CI, type safety) — not a review of the actual code.

Overall score 7/10

AI's overall editorial judgment — not an average of the bars above, can weigh other factors too.

llm recommender-systems nlp survey research

MIT licensed Educational Niche/specialized use case Beginner friendly

Deep Analysis · Based on README and public signals

1w ago

Curated survey on LLM applications in recommender systems with peer-reviewed backing

Awesome-LLM-for-RecSys is a literature curation and taxonomy resource documenting how large language models are integrated into recommendation pipelines. It anchors a published ACM TOIS survey paper (2024) and organizes papers by where LLMs are deployed: feature engineering, ranking, reranking, explanation, and reasoning. Built for researchers and practitioners exploring LLM-RecSys intersections. The repo serves as a living index rather than a software tool or framework.

Origin

Launched May 2023 as the LLM boom accelerated. Evolved from initial paper collection to a formal survey accepted by ACM TOIS in 2024, with camera-ready v6 released July 2024. Maintains weekly research updates via WeChat community channel. Represents the maturation phase of LLM-for-RecSys as an academic subfield.

Growth

Peaked at acquisition phase (2023–early 2024) following survey publication. Gained ~1,545 stars over ~3 years, averaging ~1 star per week recently. Growth reflects stable interest in the topic rather than viral adoption. Forks (88) and weekly star gain (1) suggest steady but modest engagement. The publication in a top-tier venue (TOIS) lent credibility but did not drive exponential adoption, consistent with academic survey resources.

In production

Adoption not verified in production systems. The resource is a survey index, not a deployable framework. Usage is inferred to be academic (researchers, students) and possibly by industry practitioners surveying the landscape. No GitHub Issues, PRs, or external integrations documented. Citation count of the underlying survey paper (if available on ACM/Google Scholar) would be a better adoption proxy than repository stars.

Code analysis

Architecture

Not a software project. Repository structure is documentation-based: markdown tables categorizing papers by application point in the RecSys pipeline (feature engineering, ranking, reranking, explanation, reasoning). README includes reference tables with paper name, LLM backbone, tuning strategy, venue, and link. Likely organized as a static resource with periodic manual updates.

Tests

Not applicable; this is a curated resource, not executable code.

Maintenance

Last push 2026-01-17 (approximately 5 months ago as of 2026-07-01). Survey paper archived July 2024. README indicates ongoing updates to 'Newest Research Work List' (section 1.7 mentioned), and author claims weekly WeChat paper notes. Updates appear periodic and driven by author's manual curation rather than automated processes. Maintenance is active but low-velocity, consistent with survey maintenance patterns.

Honest verdict

ADOPT IF: you are a researcher or practitioner systematically surveying LLM applications in recommender systems and need a curated, peer-reviewed taxonomy of the landscape. AVOID IF: you are looking for executable code, a production framework, or a tool with active community support and integration guides. MONITOR IF: the field continues to evolve rapidly; this resource may become outdated if the author reduces curation frequency, though the archived TOIS survey provides stable historical reference.

Independent dimensions

Mainstream potential

2/10

Technical importance

5/10

Adoption evidence

3/10

Risks

Single maintainer dependency: curation relies on one author (CHIANGEL); discontinuation risk if author moves on.
Curation lag: manual updates mean papers may be added weeks or months after publication; no automated detection of new relevant work.
No versioning or releases: repository is a single branch; no tagged snapshots tied to survey paper versions, making historical citation imprecise.
Limited quality filtering: being a curated list, there is no explicit peer review of included papers beyond venue selection; inclusion criteria not formally documented.
Static resource ceiling: as markdown tables, the resource does not scale well to hundreds of papers; search/filter usability may degrade without tooling.

Prediction

Repository will likely remain a niche but stable academic resource. As the LLM-RecSys field matures, the value of this survey decreases unless it evolves into a searchable database or community-driven platform. Most probable outcome: slow maintenance as a static archive with occasional updates, cited by researchers but not widely adopted outside the academic community.

0 found this helpful

Explore similar

Hannibal046/Awesome-LLM TsinghuaC3I/Awesome-RL-for-LRMs WangRongsheng/awesome-LLM-resources WooooDyy/LLM-Agent-Paper-List

Newsletter

Get analyses like this every Monday

Free weekly digest of the most interesting open-source discoveries.

Languages

No language breakdown available.

Information

License: MIT
Last updated: 6mo ago
Created: 38mo ago
Analyzed with: anthropic/claude-haiku-4-5

Stars over time

Loading…

Contributors over time

Top 100 contributors only — repos with more will plateau at 100.

Loading…

Open issues

Add StoryRoute - LLM travel recommendation and storytelling app

samirasadov28-code 1 22 Mar 2026

Request to add ACL 2024 Paper [BinLLM]

zyang1580 10 Mar 2025

Open pull requests

Survey Paper Added

arpita8 13 Aug 2024

New paper on user/action alignement

Nicolas99-9 06 Jan 2026

Add OpenClaw Monitor

flik2002 23 May 2026

Top contributors

CHIANGEL

weiwei1206

danicrg

eltociear

hyc9

Recent releases

No releases published yet.

Similar repos

Hannibal046/Awesome-LLM

Awesome-LLM is a curated index of Large Language Model resources, including...

27.1k AI & ML

TsinghuaC3I/Awesome-RL-for-LRMs

This is a curated survey and collection of papers on reinforcement learning...

2.5k TeX AI & ML

WangRongsheng/awesome-LLM-resources

This is a curated index of Large Language Model resources, covering multimodal...

8.7k AI & ML

WooooDyy/LLM-Agent-Paper-List

This is a curated paper list repository accompanying an 86-page survey on Large...

8.2k AI & ML

Repository	Stars	Week Δ	Language	Score	Updated
CHIANGEL/Awesome-LLM-for-RecSys this	1.5k	+2	—	7/10	6mo ago
Hannibal046/Awesome-LLM	27.1k	—	—	7/10	11mo ago
TsinghuaC3I/Awesome-RL-for-LRMs	2.5k	—	TeX	8/10	8mo ago
WangRongsheng/awesome-LLM-resources	8.7k	—	—	7/10	8h ago
WooooDyy/LLM-Agent-Paper-List	8.2k	—	—	7/10	10mo ago

vs. alternatives

Hannibal046/Awesome-LLM

Broader LLM survey (27k stars) covering general LLM applications; this repo is narrowly focused on recommender systems, serving a specialized intersection rather than competing directly.

WooooDyy/LLM-Agent-Paper-List

Covers LLM-based agents (8k stars); overlaps minimally since this repo emphasizes RecSys pipelines, not autonomous agents.

WangRongsheng/awesome-LLM-resources

General LLM resources collection (8.6k stars); more general-purpose; this repo offers deeper taxonomy for RecSys-specific LLM integration patterns.

TsinghuaC3I/Awesome-RL-for-LRMs

Focuses on reinforcement learning for large robotic models; entirely different domain, no meaningful overlap.

Name	Paper	LLM Backbone (Largest)	LLM Tuning Strategy	Publication	Link
LLM4KGC	Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs	PaLM (540B)/ ChatGPT	Frozen	Arxiv 2023	[Link]
TagGPT	TagGPT: Large Language Models are Zero-shot Multimodal Taggers	ChatGPT	Frozen	Arxiv 2023	[Link]
ICPC	Large Language Models for User Interest Journeys	LaMDA (137B)	Full Finetuning/ Prompt Tuning	Arxiv 2023	[Link]
KAR	Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models	ChatGPT	Frozen	Arxiv 2023	[Link]
PIE	Product Information Extraction using ChatGPT	ChatGPT	Frozen	Arxiv 2023	[Link]
LGIR	Enhancing Job Recommendation through LLM-based Generative Adversarial Networks	GhatGLM (6B)	Frozen	AAAI 2024	[Link]
GIRL	Generative Job Recommendations with Large Language Model	BELLE (7B)	Full Finetuning	Arxiv 2023	[Link]
LLM-Rec	LLM-Rec: Personalized Recommendation via Prompting Large Language Models	text-davinci-003	Frozen	Arxiv 2023	[Link]
HKFR	Heterogeneous Knowledge Fusion: A Novel Approach for Personalized Recommendation via LLM	ChatGPT	Frozen	RecSys 2023	[Link]
LLaMA-E	LLaMA-E: Empowering E-commerce Authoring with Multi-Aspect Instruction Following	LLaMA (30B)	LoRA	Arxiv 2023	[Link]
EcomGPT	EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce	BLOOMZ (7.1B)	Full Finetuning	Arxiv 2023	[Link]
TF-DCon	Leveraging Large Language Models (LLMs) to Empower Training-Free Dataset Condensation for Content-Based Recommendation	ChatGPT	Frozen	Arxiv 2023	[Link]
RLMRec	Representation Learning with Large Language Models for Recommendation	ChatGPT	Frozen	WWW 2024	[Link]
LLMRec	LLMRec: Large Language Models with Graph Augmentation for Recommendation	ChatGPT	Frozen	WSDM 2024	[Link]
LLMRG	Enhancing Recommender Systems with Large Language Model Reasoning Graphs	GPT4	Frozen	Arxiv 2023	[Link]
CUP	Recommendations by Concise User Profiles from Review Text	ChatGPT	Frozen	Arxiv 2023	[Link]
SINGLE	Modeling User Viewing Flow using Large Language Models for Article Recommendation	ChatGPT	Frozen	Arxiv 2023	[Link]
SAGCN	Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models	Vicuna (13B)	Frozen	Arxiv 2023	[Link]
UEM	User Embedding Model for Personalized Language Prompting	FLAN-T5-base (250M)	Full Finetuning	Arxiv 2024	[Link]
LLMHG	LLM-Guided Multi-View Hypergraph Learning for Human-Centric Explainable Recommendation	GPT4	Frozen	Arxiv 2024	[Link]
Llama4Rec	Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation	LLaMA2 (7B)	Full Finetuning	Arxiv 2024	[Link]
LLM4Vis	LLM4Vis: Explainable Visualization Recommendation using ChatGPT	ChatGPT	Frozen	EMNLP 2023	[Link]
LoRec	LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks	LLaMA2	Frozen	SIGIR 2024	[Link]

Name	Paper	LLM Backbone (Largest)	LLM Tuning Strategy	Publication	Link
RecInter	Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems	GPT-4o	Frozen	EMNLP 2025	[Link]
GReaT	Language Models are Realistic Tabular Data Generators	GPT2-medium (355M)	Full Finetuning	ICLR 2023	[Link]
ONCE	ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models	ChatGPT	Frozen	WSDM 2024	[Link]
AnyPredict	AnyPredict: Foundation Model for Tabular Prediction	ChatGPT	Frozen	Arxiv 2023	[Link]
DPLLM	Privacy-Preserving Recommender Systems with Synthetic Query Generation using Differentially Private Large Language Models	T5-XL (3B)	Full Finetuning	Arxiv 2023	[Link]
MINT	Large Language Model Augmented Narrative Driven Recommendations	text-davinci-003	Frozen	RecSys 2023	[Link]
Agent4Rec	On Generative Agents in Recommendation	ChatGPT	Frozen	Arxiv 2023	[Link]
RecPrompt	RecPrompt: A Prompt Tuning Framework for News Recommendation Using Large Language Models	GPT4	Frozen	Arxiv 2023	[Link]
PO4ISR	Large Language Models for Intent-Driven Session Recommendations	ChatGPT	Frozen	Arxiv 2023	[Link]
BEQUE	Large Language Model based Long-tail Query Rewriting in Taobao Search	ChatGLM (6B)	FFT	Arxiv 2023	[Link]
Agent4Ranking	Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLM	ChatGPT	Frozen	Arxiv 2023	[Link]
PopNudge	Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation	ChatGPT	Frozen	Arxiv 2023	[Link]

Name	Paper	LLM Backbone (Largest)	LLM Tuning Strategy	Publication	Link
U-BERT	U-BERT: Pre-training User Representations for Improved Recommendation	BERT-base (110M)	Full Finetuning	AAAI 2021	[Link]
UNBERT	UNBERT: User-News Matching BERT for News Recommendation	BERT-base (110M)	Full Finetuning	IJCAI 2021	[Link]
PLM-NR	Empowering News Recommendation with Pre-trained Language Models	RoBERTa-base (125M)	Full Finetuning	SIGIR 2021	[Link]
Pyramid-ERNIE	Pre-trained Language Model based Ranking in Baidu Search	ERNIE (110M)	Full Finetuning	KDD 2021	[Link]
ERNIE-RS	Pre-trained Language Model for Web-scale Retrieval in Baidu Search	ERNIE (110M)	Full Finetuning	KDD 2021	[Link]
CTR-BERT	CTR-BERT: Cost-effective knowledge distillation for billion-parameter teacher models	Customized BERT (1.5B)	Full Finetuning	ENLSP 2021	[Link]
SuKD	Learning Supplementary NLP Features for CTR Prediction in Sponsored Search	RoBERTa-large (355M)	Full Finetuning	KDD 2022	[Link]
PREC	Boosting Deep CTR Prediction with a Plug-and-Play Pre-trainer for News Recommendation	BERT-base (110M)	Full Finetuning	COLING 2022	[Link]
MM-Rec	MM-Rec: Visiolinguistic Model Empowered Multimodal News Recommendation	BERT-base (110M)	Full Finetuning	SIGIR 2022	[Link]
Tiny-NewsRec	Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation	UniLMv2-base (110M)	Full Finetuning	EMNLP 2022	[Link]
PLM4Tag	PTM4Tag: Sharpening Tag Recommendation of Stack Overflow Posts with Pre-trained Models	CodeBERT (125M)	Full Finetuning	ICPC 2022	[Link]
TwHIN-BERT	TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations	BERT-base (110M)	Full Finetuning	Arxiv 2022	[Link]
LSH	Improving Code Example Recommendations on Informal Documentation Using BERT and Query-Aware LSH: A Comparative Study	BERT-base (110M)	Full Finetuning	Arxiv 2023	[Link]
LLM2BERT4Rec	Leveraging Large Language Models for Sequential Recommendation	text-embedding-ada-002	Frozen	RecSys 2023	[Link]
LLM4ARec	Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations	GPT2 (110M)	Prompt Tuning	Arxiv 2023	[Link]
TIGER	Recommender Systems with Generative Retrieval	Sentence-T5-base (223M)	Frozen	NIPS 2023	[Link]
TBIN	TBIN: Modeling Long Textual Behavior Data for CTR Prediction	BERT-base (110M)	Frozen	DLP-RecSys 2023	[Link]
LKPNR	LKPNR: LLM and KG for Personalized News Recommendation Framework	LLaMA2 (7B)	Frozen	Arxiv 2023	[Link]
SSNA	Towards Efficient and Effective Adaptation of Large Language Models for Sequential Recommendation	DistilRoBERTa-base (83M)	Layerwise Adapter Tuning	Arxiv 2023	[Link]
CollabContext	Collaborative Contextualization: Bridging the Gap between Collaborative Filtering and Pre-trained Language Model	Instructor-XL (1.5B)	Frozen	Arxiv 2023	[Link]
LMIndexer	Language Models As Semantic Indexers	T5-base (223M)	Full Finetuning	Arxiv 2023	[Link]
Stack	A BERT based Ensemble Approach for Sentiment Classification of Customer Reviews and its Application to Nudge Marketing in e-Commerce	BERT-base (110M)	Frozen	Arxiv 2023	[Link]
N/A	Utilizing Language Models for Tour Itinerary Recommendation	BERT-base (110M)	Full Finetuning	PMAI@IJCAI 2023	[Link]
UEM	User Embedding Model for Personalized Language Prompting	Sentence-T5-base (223M)	Frozen	Arxiv 2024	[Link]
Social-LLM	Social-LLM: Modeling User Behavior at Scale using Language Models and Social Network Data	SBERT-MPNet-base (110M)	Frozen	Arxiv 2024	[Link]
LLMRS	LLMRS: Unlocking Potentials of LLM-Based Recommender Systems for Software Purchase	MPNet (110M)	Frozen	Arxiv 2024	[Link]
KERL	Knowledge Graphs and Pre-trained Language Models enhanced Representation Learning for Conversational Recommender Systems	BERT-mini	Frozen	TNNLS	[Link]
N/A	Empowering Few-Shot Recommender Systems with Large Language Models -- Enhanced Representations	ChatGPT	Frozen	IEEE Access	[Link]
N/A	Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations	Unknown	Frozen	Arxiv 2023	[Link]

Name	Paper	LLM Backbone (Largest)	LLM Tuning Strategy	Publication	Link
ZESRec	Zero-Shot Recommender Systems	BERT-base (110M)	Frozen	Arxiv 2021	[Link]
UniSRec	Towards Universal Sequence Representation Learning for Recommender Systems	BERT-base (110M)	Frozen	KDD 2022	[Link]
TransRec	TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback	BERT-base (110M)	Full Finetuning	Arxiv 2022	[Link]
VQ-Rec	Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders	BERT-base (110M)	Frozen	WWW 2023	[Link]
IDRec vs MoRec	Where to Go Next for Recommender Systems? ID- vs. Modality-based Recomm

CHIANGEL/Awesome-LLM-for-RecSys

AI Analysis

Curated survey on LLM applications in recommender systems with peer-reviewed backing

Get analyses like this every Monday

Languages

Information

Stars over time

Contributors over time

Open issues

Open pull requests

Top contributors

Recent releases

Similar repos

Awesome-LLM-for-RecSys

1. Papers