Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.27856 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913166447869952 |
|---|---|
| author | Yang, Hui He, Daiwei Jiang, Kevin Park, Taejin Li, Kungang Luo, Jiajun Chen, Yuying Zhang, Xinyi Wang, Sihan He, Haoyu Liu, Yu Manoharan, Lakshmi Xue, David Barhate, Shubham Su, Runze Zhan, Duna Leng, Ling Ji, Siping Zhuang, Jinfeng Wu, Alice Lu, Leo Sun, Han Liu, Zhifang |
| author_facet | Yang, Hui He, Daiwei Jiang, Kevin Park, Taejin Li, Kungang Luo, Jiajun Chen, Yuying Zhang, Xinyi Wang, Sihan He, Haoyu Liu, Yu Manoharan, Lakshmi Xue, David Barhate, Shubham Su, Runze Zhan, Duna Leng, Ling Ji, Siping Zhuang, Jinfeng Wu, Alice Lu, Leo Sun, Han Liu, Zhifang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27856 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fine-Tuned LLM as a Complementary Predictor Improving Ads System Yang, Hui He, Daiwei Jiang, Kevin Park, Taejin Li, Kungang Luo, Jiajun Chen, Yuying Zhang, Xinyi Wang, Sihan He, Haoyu Liu, Yu Manoharan, Lakshmi Xue, David Barhate, Shubham Su, Runze Zhan, Duna Leng, Ling Ji, Siping Zhuang, Jinfeng Wu, Alice Lu, Leo Sun, Han Liu, Zhifang Information Retrieval Artificial Intelligence 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. |
| title | Fine-Tuned LLM as a Complementary Predictor Improving Ads System |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2605.27856 |