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

arXiv: https://arxiv.org/abs/2602.03097 · HTML: https://mlsanity.com/paper/2602.03097/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 18 of its 61 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)
- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 18 of 18)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems](https://mlsanity.com/paper/2205.08084/) (2022)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking](https://mlsanity.com/paper/2311.02089/) (2023)
- [NoteLLM-2: Multimodal Large Representation Models for Recommendation](https://mlsanity.com/paper/2405.16789/) (2024)
- [TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis](https://mlsanity.com/paper/2410.04047/) (2024)
- [Rethinking Large Language Model Architectures for Sequential Recommendations](https://mlsanity.com/paper/2402.09543/) (2024)
- [A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models](https://mlsanity.com/paper/2509.11575/) (2025)
- [Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2509.03817/) (2025)
- [HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL](https://mlsanity.com/paper/2503.16528/) (2025)
- [Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs](https://mlsanity.com/paper/2511.06134/) (2025)
- [Generative Job Recommendations with Large Language Model](https://mlsanity.com/paper/2307.02157/) (2023)
- [Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2601.21919/) (2026)
- [ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Models](https://mlsanity.com/paper/2502.11059/) (2025)
- [TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation](https://mlsanity.com/paper/2508.15388/) (2025)
- [Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models](https://mlsanity.com/paper/2412.04107/) (2024)

## Built on by (most cited first, 2 of 2)

- [SatIR: Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching](https://mlsanity.com/paper/2604.08849/) (2026)
- [Rethinking Fairness in LLM-Based Recommender Systems: A Survey](https://mlsanity.com/paper/2606.28340/) (2026)

## Abstract (arXiv)

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.