Related papers: LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains

LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains

URL: http://arxiv.org/abs/2604.16379v1
Date: Wed, 25 Mar 2026 02:49:27 GMT
Title: LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains
Abstract summary: Industrial B2B applications face extreme data sparsity yet feature rich textual interactions.<n>We propose LLMAR (LLM-Annotated Recommendation), a tuning-free framework.<n>We introduce three core contributions: Inference-Driven, Reflection Loop, and Cost-Effective Architecture.
Score: 0.0
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Industrial B2B applications (e.g., construction site risk prediction, material procurement) face extreme data sparsity yet feature rich textual interactions. In such environments, traditional ID-based collaborative filtering fails lacking co-occurrence signals, while fine-tuning standard Large Language Models (LLMs) incurs high operational costs and struggles with frequent data drift. We propose LLMAR (LLM-Annotated Recommendation), a tuning-free framework. Moving beyond simple embeddings, LLMAR systematically integrates LLM reasoning to capture user "latent motives" without any training process. We introduce three core contributions: (1) Inference-Driven Annotation: uses LLMs to transform behavioral history into structured semantic motives, enabling reasoning-based matching unattainable by ID-based methods; (2) Reflection Loop: a self-correction mechanism that refines generated queries to mitigate hallucinations and resolve "context competition" between past history and current instructions; and (3) Cost-Effective Architecture: relies on tuning-free components and asynchronous batch processing to minimize maintenance costs. Evaluations on public benchmarks (MovieLens-1M, Amazon Prime Pantry) and a sparse industrial dataset (construction risk prediction) demonstrate that LLMAR outperforms state-of-the-art learning-based models (SASRecF), achieving up to a 54.6% nDCG@10 improvement on the industrial dataset. Inference costs remain highly practical (~$1 per 1,000 users). For B2B domains where strict real-time latency is not critical, combining LLM reasoning with self-verification offers a superior alternative to training-based approaches across accuracy, explainability, and operational cost.

Related papers

FLARE: Diffusion for Hybrid Language Model [72.60770374799634]
FLARE is a systematic conversion framework for hybrid-attention large language models.<n>It combines a token-equal AR-and-diffusion objective, hardware-aware kernels, and unified inference, enabling one checkpoint to support both AR-style verified decoding and diffusion-style parallel denoising.<n>Our results suggest practical dLLMs are limited not only by decoding algorithms, but also by transfer data quality and the training inefficiency of current block-diffusion objectives.
arXiv Detail & Related papers (2026-06-01T06:58:15Z)
Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies [0.9867902290081937]
Grounded claim factuality checking is important for large language model (LLM) applications such as retrieval-augmented generation.<n>We address this by formulating grounded claim factuality checking as a true/false reading comprehension task.<n>Our method reduces token usage by over 80% compared to unguided open-ended reasoning.
arXiv Detail & Related papers (2026-05-28T10:11:42Z)
Federated Reasoning Distillation Framework with Model Learnability-Aware Data Allocation [33.153769672977035]
We propose LaDa, a federated reasoning distillation framework with model learnability-aware data allocation.<n>LaDa operates as a plug-in module for existing collaboration frameworks, adapting knowledge transfer based on model learnability gaps.
arXiv Detail & Related papers (2026-02-21T08:18:39Z)
DiffuRank: Effective Document Reranking with Diffusion Language Models [71.16830004674513]
We propose DiffuRank, a reranking framework built upon diffusion language models (dLLMs)<n>dLLMs support more flexible decoding and generation processes that are not constrained to a left-to-right order.<n>We show dLLMs achieve performance comparable to, and in some cases exceeding, that of autoregressive LLMs with similar model sizes.
arXiv Detail & Related papers (2026-02-13T02:18:14Z)
From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning [81.97788535387286]
We propose a framework that internalizes the agentic verification-and-editing mechanism into a unified, single-pass inference process.<n>With minimal data, SRI-Coder enables Chat models to surpass the completion performance of their Base counterparts.<n>Unlike FIM-style tuning, SRI preserves general coding competencies and maintains inference latency comparable to standard FIM.
arXiv Detail & Related papers (2026-01-19T20:33:53Z)
SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models [53.19726629537694]
Post-training alignment of video generation models with human preferences is a critical goal.<n>Current data collection paradigms, reliant on in-prompt pairwise annotations, suffer from labeling noise.<n>We propose SoliReward, a systematic framework for video RM training.
arXiv Detail & Related papers (2025-12-17T14:28:23Z)
OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning [44.346973471913856]
We present OR-R1, a data-efficient training framework for automated optimization modeling and solving.<n>Experiments show that OR-R1 achieves state-of-the-art performance with an average solving accuracy of $67.7%$.
arXiv Detail & Related papers (2025-11-12T08:05:31Z)
LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing [42.51773265892766]
Retrieval Augmented Generation (RAG) systems often struggle with domain-specific knowledge due to performance deterioration of pre-trained embeddings.<n>We propose LMAR (Language Model Augmented Retriever), a model-agnostic framework that addresses these challenges by combining LLM-guided data synthesis with contrastive embedding adaptation and efficient text clustering.
arXiv Detail & Related papers (2025-08-04T16:59:43Z)
Enhancing Temporal Sensitivity of Large Language Model for Recommendation with Counterfactual Tuning [8.798364656768657]
We propose a framework for underlineRecommendation (CETRec)<n> CETRec is grounded in causal inference principles, which allow it to isolate and measure the specific impact of temporal information on recommendation outcomes.<n>Our code is available at https://anonymous.4open.science/r/CETRec-B9CE/.
arXiv Detail & Related papers (2025-07-03T10:11:35Z)
Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
arXiv Detail & Related papers (2025-01-31T17:19:57Z)
Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions [59.5243730853157]
Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets.<n>This article conducts a comparative analysis of three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues.
arXiv Detail & Related papers (2025-01-08T11:37:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.