AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

Jie Zhu, Huaixia Dou, Junhui Li, Lifan Guo, Feng Chen, Chi Zhang, Fang Kong

AAAI 2026 · Large language models › Instruction and fine-tuning · approach: Fine-tuning for reasoning data · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune on RoleCSLLaMA3.1-Instruct 8B · CSConv (reference context)strategy accuracy: 17.16 -> 42.15Improved
fine-tune on RoleCSQwen2.5-Instruct 7B · CSConv (reference context)strategy accuracy: 18.78 -> 42.96Improved
fine-tune on RoleCSQwen2.5-Instruct 72B · CSConv (reference context)strategy accuracy: 37.22 -> 43.29Improved
fine-tune on RoleCSQwen2.5-Instruct 7B · CSConv (generated context)strategy accuracy: 19.39 -> 30.52Improved
fine-tune on RoleCSQwen2.5-Instruct 72B · CSConv (generated context)strategy accuracy: 30.93 -> 36.02Improved
use role-playing instead of in-context generation for synthetic data (ablation)Qwen2.5-7B SFT · CSConvstrategy accuracy: 33.09 -> 36.17Improved
add Supporter Assistant agent to role-playing (ablation)Qwen2.5-7B SFT · CSConvstrategy accuracy: 36.17 -> 42.96Improved
increase synthetic data beyond first 3K dialogues (ablation)Qwen2.5-7B SFT · CSConvBLEU-4 / ROUGE-L / BERTScoreNo clear effect
predict strategy before responding vs none (ablation)Qwen2.5-72B-Instruct · CSConvBLEU-4: 3.11 -> 3.23Improved
provide oracle strategy instead of predicted (ablation)Qwen2.5-72B-Instruct · CSConvBLEU-4: 3.23 -> 3.80Improved
rewrite real conversations with LLM to use strategiesCSConv · strategy use ratestrategy use: 55.28% -> 97.82%Improved
evaluate with model-generated history instead of gold historyall LLMs · CSConvstrategy accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy