On Reasoning Behind Next Occupation Recommendation

2026-04-22

AI Summary

This work addresses the limited ability of large language models (LLMs) to comprehend career trajectories and underlying decision motives in next-job recommendation tasks. To overcome this, the authors propose a two-stage reasoning framework: a rationale generator first produces high-quality, preference-reflecting “rationales” based on users’ educational and occupational histories, which are then used as contextual input for a job predictor. By fine-tuning a single model with human-annotated “Oracle rationales” to jointly perform rationale generation and job prediction, the approach significantly outperforms both decoupled architectures and unsupervised baselines. Experimental results show that prediction accuracy approaches fully supervised performance and strongly correlates with rationale quality. Furthermore, employing LLM-as-a-Judge enables automated evaluation and generation of factually grounded, coherent, and useful rationales, effectively facilitating fine-tuning of smaller models.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

In this work, we develop a novel reasoning approach to enhance the performance of large language models (LLMs) in future occupation prediction. In this approach, a reason generator first derives a ``reason'' for a user using his/her past education and career history. The reason summarizes the user's preference and is used as the input of an occupation predictor to recommend the user's next occupation. This two-step occupation prediction approach is, however, non-trivial as LLMs are not aligned with career paths or the unobserved reasons behind each occupation decision. We therefore propose to fine-tune LLMs improving their reasoning and occupation prediction performance. We first derive high-quality oracle reasons, as measured by factuality, coherence and utility criteria, using a LLM-as-a-Judge. These oracle reasons are then used to fine-tune small LLMs to perform reason generation and next occupation prediction. Our extensive experiments show that: (a) our approach effectively enhances LLM's accuracy in next occupation prediction making them comparable to fully supervised methods and outperforming unsupervised methods; (b) a single LLM fine-tuned to perform reason generation and occupation prediction outperforms two LLMs fine-tuned to perform the tasks separately; and (c) the next occupation prediction accuracy depends on the quality of generated reasons. Our code is available at https://github.com/Sarasarahhhhh/job_prediction.

Problem

• next occupation prediction
• large language models
• reasoning
• career path
• occupation recommendation

Innovation

• reasoning
• large language models
• occupation prediction
• fine-tuning
• LLM-as-a-Judge