Guardado en:
Detalles Bibliográficos
Autores principales: Fu, Zhoutong, Cao, Yihan, Chen, Yi-Lin, Lunia, Aman, Dong, Liming, Saraf, Neha, Jiang, Ruijie, Dai, Yun, Song, Qingquan, Wang, Tan, Li, Guoyao, Koh, Derek, Wei, Haichao, Wang, Zhipeng, Gupta, Aman, Jiang, Chengming, Shen, Jianqiang, Hong, Liangjie, Zhang, Wenjing
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.05490
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911195514011648
author Fu, Zhoutong
Cao, Yihan
Chen, Yi-Lin
Lunia, Aman
Dong, Liming
Saraf, Neha
Jiang, Ruijie
Dai, Yun
Song, Qingquan
Wang, Tan
Li, Guoyao
Koh, Derek
Wei, Haichao
Wang, Zhipeng
Gupta, Aman
Jiang, Chengming
Shen, Jianqiang
Hong, Liangjie
Zhang, Wenjing
author_facet Fu, Zhoutong
Cao, Yihan
Chen, Yi-Lin
Lunia, Aman
Dong, Liming
Saraf, Neha
Jiang, Ruijie
Dai, Yun
Song, Qingquan
Wang, Tan
Li, Guoyao
Koh, Derek
Wei, Haichao
Wang, Zhipeng
Gupta, Aman
Jiang, Chengming
Shen, Jianqiang
Hong, Liangjie
Zhang, Wenjing
contents Large language models (LLMs) have achieved strong performance across a wide range of natural language processing tasks. However, deploying LLMs at scale for domain specific applications, such as job-person fit and explanation in job seeking platforms, introduces distinct challenges. At LinkedIn, the job person fit task requires analyzing a candidate's public profile against job requirements to produce both a fit assessment and a detailed explanation. Directly applying open source or finetuned LLMs to this task often fails to yield high quality, actionable feedback due to the complexity of the domain and the need for structured outputs. Moreover, the large size of these models leads to high inference latency and limits scalability, making them unsuitable for online use. To address these challenges, we introduce LANTERN, a novel LLM knowledge distillation framework tailored specifically for job person fit tasks. LANTERN involves modeling over multiple objectives, an encoder model for classification purpose, and a decoder model for explanation purpose. To better distill the knowledge from a strong black box teacher model to multiple downstream models, LANTERN incorporates multi level knowledge distillation that integrates both data and logit level insights. In addition to introducing the knowledge distillation framework, we share our insights on post training techniques and prompt engineering, both of which are crucial for successfully adapting LLMs to domain specific downstream tasks. Extensive experimental results demonstrate that LANTERN significantly improves task specific metrics for both job person fit and explanation. Online evaluations further confirm its effectiveness, showing measurable gains in job seeker engagement, including a 0.24\% increase in apply rate and a 0.28\% increase in qualified applications.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05490
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LANTERN: Scalable Distillation of Large Language Models for Job-Person Fit and Explanation
Fu, Zhoutong
Cao, Yihan
Chen, Yi-Lin
Lunia, Aman
Dong, Liming
Saraf, Neha
Jiang, Ruijie
Dai, Yun
Song, Qingquan
Wang, Tan
Li, Guoyao
Koh, Derek
Wei, Haichao
Wang, Zhipeng
Gupta, Aman
Jiang, Chengming
Shen, Jianqiang
Hong, Liangjie
Zhang, Wenjing
Computation and Language
Artificial Intelligence
Large language models (LLMs) have achieved strong performance across a wide range of natural language processing tasks. However, deploying LLMs at scale for domain specific applications, such as job-person fit and explanation in job seeking platforms, introduces distinct challenges. At LinkedIn, the job person fit task requires analyzing a candidate's public profile against job requirements to produce both a fit assessment and a detailed explanation. Directly applying open source or finetuned LLMs to this task often fails to yield high quality, actionable feedback due to the complexity of the domain and the need for structured outputs. Moreover, the large size of these models leads to high inference latency and limits scalability, making them unsuitable for online use. To address these challenges, we introduce LANTERN, a novel LLM knowledge distillation framework tailored specifically for job person fit tasks. LANTERN involves modeling over multiple objectives, an encoder model for classification purpose, and a decoder model for explanation purpose. To better distill the knowledge from a strong black box teacher model to multiple downstream models, LANTERN incorporates multi level knowledge distillation that integrates both data and logit level insights. In addition to introducing the knowledge distillation framework, we share our insights on post training techniques and prompt engineering, both of which are crucial for successfully adapting LLMs to domain specific downstream tasks. Extensive experimental results demonstrate that LANTERN significantly improves task specific metrics for both job person fit and explanation. Online evaluations further confirm its effectiveness, showing measurable gains in job seeker engagement, including a 0.24\% increase in apply rate and a 0.28\% increase in qualified applications.
title LANTERN: Scalable Distillation of Large Language Models for Job-Person Fit and Explanation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.05490