Fine-Tuned LLM as a Complementary Predictor Improving Ads System

• URL: http://arxiv.org/abs/2605.27856v1
• Date: Wed, 27 May 2026 02:19:40 GMT
• Title: Fine-Tuned LLM as a Complementary Predictor Improving Ads System
• Abstract summary: We introduce a complementary paradigm for ads: a fine-tuned open-source LLM used not as a ranker, but as an ads-specific ancillary predictor.<n>This LLM-driven advertiser prediction augments conventional candidate generation and provides informative priors to downstream ranking.<n>Our results show that targeted ancillary predictions can unlock end-to-end gains across both retrieval and late-stage ranking.
• Score: 19.090316915560827
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recommendation systems power engagement and monetization across feeds, ads, and short-video platforms, but translating the latest advances in Large Language Models into Recommendation Systems (RecSys) gains remains rare, particularly in advertising and production-scale real-world industry setups. Prior real-world LLM successes typically fall into three buckets: (a) generative retrieval that directly predicts the next items for candidate generation, (b) late-stage re-ranking that uses LLMs, and (c) auxiliary signal enrichment with LLMs. We introduce a complementary paradigm for ads: a fine-tuned open-source LLM used not as a ranker, but as an ads-specific ancillary predictor, forecasting likely advertisers from user profiles and histories. This LLM-driven advertiser prediction augments conventional candidate generation and provides informative priors to downstream ranking. Developed in a large-scale production advertising system, our approach produces substantial offline improvements and measurable online business impact, demonstrating that LLM world knowledge and predictive capacity can be efficiently harnessed. Beyond validating LLMs for ads applications, our results show that targeted ancillary predictions can unlock end-to-end gains across both retrieval and late-stage ranking, offering a practical path to LLM-enhanced recommendation at scale.

Related papers

• LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks [10.426127907431772]
  LLM-HYPER treats large language models as hypernetworks to generate the parameters of the click-through rate (CTR) estimator in a training-free manner.<n>Extensive offline experiments show that LLM-HYPER significantly outperforms cold-start baselines in NDCG$@10$ by 55.9%.<n>Our real-world online A/B test on one of the top e-commerce platforms in the U.S. demonstrates the strong performance of LLM-HYPER.
  arXiv  Detail & Related papers  (2026-04-13T22:12:40Z)
• LLM-Auction: Generative Auction towards LLM-Native Advertising [10.695066036409274]
  We propose a learning-based generative auction mechanism that integrates auction and LLM generation for LLM-native advertising.<n>We introduce Iterative Reward-Preference Optimization (IRPO) algorithm that alternately optimize the reward model and the LLM.<n>We show that LLM-Auction significantly outperforms existing baselines in allocation efficiency, while achieving the desired mechanism properties.
  arXiv  Detail & Related papers  (2025-12-11T11:31:20Z)
• Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models [54.38054999271322]
  We show that large language models (LLMs) don't update their beliefs as expected from the Bayesian framework.<n>We teach the LLMs to reason in a Bayesian manner by training them to mimic the predictions of the normative Bayesian model.<n>More generally, our results indicate that LLMs can effectively learn reasoning skills from examples and generalize those skills to new domains.
  arXiv  Detail & Related papers  (2025-03-21T20:13:04Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• Best Practices for Distilling Large Language Models into BERT for Web Search Ranking [14.550458167328497]
  Large Language Models (LLMs) can generate a ranked list of potential documents. We transfer the ranking expertise of LLMs to a more compact model like BERT, using a ranking loss to enable the deployment of less resource-intensive models. Our model has been successfully integrated into a commercial web search engine as of February 2024.
  arXiv  Detail & Related papers  (2024-11-07T08:54:46Z)
• Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding [61.45448947483328]
  We introduce Lossless Acceleration via Speculative Decoding for LLM-based Recommender Systems (LASER)<n>LASER features a Customized Retrieval Pool to enhance retrieval efficiency and Relaxed Verification to improve the acceptance rate of draft tokens.<n>LASER achieves a 3-5x speedup on public datasets and saves about 67% of computational resources during the online A/B test.
  arXiv  Detail & Related papers  (2024-08-11T02:31:13Z)
• Truthful Aggregation of LLMs with an Application to Online Advertising [11.552000005640203]
  We introduce MOSAIC, an auction mechanism that ensures that truthful reporting is a dominant strategy for advertisers.<n>We show that MOSAIC leads to high advertiser value and platform revenue with low computational overhead.
  arXiv  Detail & Related papers  (2024-05-09T17:01:31Z)
• Large Language Models: A Survey [66.39828929831017]
  Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks.<n>LLMs' ability of general-purpose language understanding and generation is acquired by training billions of model's parameters on massive amounts of text data.
  arXiv  Detail & Related papers  (2024-02-09T05:37:09Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• Making Large Language Models Better Knowledge Miners for Online Marketing with Progressive Prompting Augmentation [33.13139821429599]
  We propose PAIR, a novel Progressive prompting Augmented mIning fRamework for harvesting marketing-oriented knowledge graph with LLMs.<n>In particular, we reduce the pure relation generation to an LLM based adaptive relation filtering process through the knowledge-empowered prompting technique.<n>In terms of online serving, we specialize in a small and white-box PAIR (i.e.,LightPAIR),which is fine-tuned with a high-quality corpus provided by a strong teacher-LLM.
  arXiv  Detail & Related papers  (2023-12-08T03:44:09Z)
• Online Advertisements with LLMs: Opportunities and Challenges [51.96140910798771]
  This paper explores the potential for leveraging Large Language Models (LLM) in the realm of online advertising systems. We introduce a general framework for LLM advertisement, consisting of modification, bidding, prediction, and auction modules.
  arXiv  Detail & Related papers  (2023-11-11T02:13:32Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.