Earticle

초록

영어

As organizations explore generative AI for customer-facing and support processes, task-specialized adaptation can improve downstream performance but weaken general conversational capabilities inherited from the base model. This trade-off is especially salient for small language models (SLMs), which are attractive for cost, latency, governance, and deployment flexibility but remain capacity-constrained on reasoning-intensive tasks. This study develops and evaluates a design-oriented stepwise post-training framework for calibrating a 1B-scale language model for bounded business applications while maintaining usable conversational quality. Using Llama-3.2-1B as the student model, the framework integrates warm-up supervised fine-tuning, stepwise reinforcement learning, rationale-consistent distillation, and selective reasoning control. The post-trained model was evaluated on customer intent inference, conversational preference, and selected PISA mathematical-reasoning items. Results suggest improvement over the base model and the same observed Pass@3 accuracy as Llama-3.2-3B on selected PISA mathematics items, with no clear evidence of degradation in limited human-preference tests. The observed gains were task-dependent, appearing more clearly in reasoning-oriented tasks than in routine classification. The study frames compact models as deployment-aware business artifacts and identifies a design logic for balancing task specialization, conversational retention, and resource-conscious model design.

목차

ABSTRACT
Ⅰ. Introduction
Ⅱ. Literature Review
2.1. Small Language Models (SLMs)
2.2. Knowledge Distillation
2.3. Prompt-Based Reasoning Elicitation Techniques
2.4. Reasoning Elicitation Through Post-Training
2.5. Stepwise Post-Training
Ⅲ. Research Framework
3.1. Framework Overview
3.2. Dataset Curation
3.3. Post-Training
Ⅳ. Results
4.1. Baselines
4.2. Evaluation Measures
4.3. Results
Ⅴ. Discussion
5.1. Findings and Implications
5.2. Limitations and Future Work
Ⅵ. Conclusion

키워드

저자

• Jinsoo Park [ Professor, College of Business Administration, Seoul National University, Korea ]
• Seungho Jeong [ Ph.D. Student, College of Business Administration, Seoul National University, Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  Asia Pacific Journal of Information Systems

• 간기

  계간

• pISSN

  2288-5404

• eISSN

  2288-6818

• 수록기간

  1990~2026

• 등재여부

  KCI 등재,SCOPUS

• 십진분류

  KDC 325 DDC 658