De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models

2026-02-03

AI Summary

This work addresses a critical limitation in existing job recommendation methods, which often conflate job seeker preferences with job qualifications, resulting in entangled supervisory signals and limited controllability of recommendation strategies. To resolve this, the authors propose JobRec, a novel framework that, for the first time, decouples preference and qualification modeling within large language models. JobRec employs a unified semantic alignment architecture and a two-stage collaborative training paradigm to separately capture these dual perspectives, further enhanced by a Lagrangian strategy alignment module to enable controllable recommendations. Leveraging expert-refined synthetic data, JobRec significantly outperforms strong baselines across multiple evaluation metrics, simultaneously improving both recommendation performance and strategic controllability.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Learning to Search
• Humans and AI: Learning Human Values and Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• 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

Professional job recommendation involves a complex bipartite matching process that must reconcile a candidate's subjective preference with an employer's objective qualification. While Large Language Models (LLMs) are well-suited for modeling the rich semantics of resumes and job descriptions, existing paradigms often collapse these two decision dimensions into a single interaction signal, yielding confounded supervision under recruitment-funnel censoring and limiting policy controllability. To address these challenges, We propose JobRec, a generative job recommendation framework for de-conflating preference and qualification via constrained dual-perspective reasoning. JobRec introduces a Unified Semantic Alignment Schema that aligns candidate and job attributes into structured semantic layers, and a Two-Stage Cooperative Training Strategy that learns decoupled experts to separately infer preference and qualification. Building on these experts, a Lagrangian-based Policy Alignment module optimizes recommendations under explicit eligibility requirements, enabling controllable trade-offs. To mitigate data scarcity, we construct a synthetic dataset refined by experts. Experiments show that JobRec consistently outperforms strong baselines and provides improved controllability for strategy-aware professional matching.

Problem

• job recommendation
• preference-qualification deconflation
• bipartite matching
• recruitment-funnel censoring
• policy controllability

Innovation

• de-conflated reasoning
• dual-perspective modeling
• semantic alignment schema
• Lagrangian policy alignment
• generative job recommendation