Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs

arXiv:2609.27262 · cs.CL · Submitted 2026-09-23 · Read on arXiv

cs.CL

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/bitext/customer-support-llm-chatbot-training-dataset

Terminology

• Fine-Tuning — 46× in this paper · explained in 5 episodes
• Adaptation — 15× in this paper · explained in 1 episode
• Robustness — 13× in this paper · explained in 5 episodes
• Model Merging — 10× in this paper · explained in 2 episodes
• Call Outcome — 9× in this paper
• Action Items — 7× in this paper
• Intent Classification — 7× in this paper
• Benchmark — 6× in this paper · explained in 2 episodes
• Call Purpose — 6× in this paper
• Generalization — 5× in this paper · explained in 13 episodes
• Meeting Summarization — 5× in this paper
• Catastrophic Forgetting — 4× in this paper · explained in 5 episodes
• Dialogue Summarization — 4× in this paper
• In International Conference on Learning Representations — 4× in this paper
• Question Answering — 4× in this paper
• Consistency — 3× in this paper · explained in 3 episodes
• In International Conference on Machine Learning — 3× in this paper
• LLM judge — 3× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Continual Learning — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Transfer Learning — 2× in this paper · explained in 10 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• LoRA Adaptation — 1× in this paper · explained in 2 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generation
• Gemma 3 Technical Report
• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• The Llama 3 Herd of Models
• Mistral 7B
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering