AI Paper Atlas

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

PsyPARSE: Retrieval-Augmented Slow Thinking for Personalized Empathetic Counseling

Longxiang Wang, Pukun Zhao, Chen Chen, Jinhe Bi, Huacan Wang, Tong Zhang, Ronghao Chen

AAAI 2026 · Large language models › Instruction and fine-tuning · approach: Fine-tuning generalization and delta compression · 1 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
add PsyPARSE framework to a general LLMDeepSeek-V3 · CPsyCounR simulated counseling, LLM eval Ctx.Ctx.: 80.51 -> 95.72Improved
add PsyPARSE to GPT-4GPT-4 · CPsyCounR simulated counseling, LLM eval Ctx.Ctx.: 66.93 -> 91.27Improved
add PsyPARSE to a small open modelLlama-3.1-8B · CPsyCounR simulated counseling, LLM eval Hum.Hum.: 60.62 -> 88.13Improved
add PsyPARSE to a fine-tuned domain modelCPsyCounX · CPsyCounR simulated counseling, LLM eval Tec.Tec.: 55.62 -> 82.17Improved
use PsyPARSE on a general 7B model instead of a fine-tuned counseling modelQwen2.5-7B vs PsycoLLM · CPsyCounR simulated counseling, LLM eval Ctx.Ctx.: 69.23 -> 88.02Improved
add PsyPARSE instead of Chain of Empathy promptingDeepSeek-V3 · CPsyCounR simulated counseling, LLM eval Tec.Tec.: 75.85 -> 95.50Improved
add Empathetic Meta-Chain promptingDeepSeek-V3 · CPsyCounR simulated counseling, LLM eval Ctx.Ctx.: 80.51 -> 78.39Hurt
add few-shot promptingDeepSeek-V3 · CPsyCounR simulated counseling, LLM eval Tec.Tec.: 75.69 -> 74.35Hurt
add multi-therapy RAG (ablation)PsyPARSE · CPsyCounR simulated counseling, LLM eval Tec.Tec.: 76.82 -> 95.50Improved
add slow-thinking engine (ablation)PsyPARSE · CPsyCounR simulated counseling, LLM eval Hum.Hum.: 84.83 -> 94.90Improved
add slow-thinking to RAG-only system (ablation)PsyPARSE · CPsyCounR simulated counseling, LLM eval Tec.Tec.: 89.47 -> 95.50Improved
use 3 rollout rounds instead of 1 (ablation)PsyPARSE · CPsyCounR simulated counseling, LLM eval Ctx.Ctx.: 88.95 -> 95.72Improved

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