From Speech to Profile: A Protocol-Driven LLM Agent for Psychological Profile Generation

TL;DR

This paper introduces StreamProfile, a streaming framework that incrementally processes counseling speech to generate accurate, traceable psychological profiles while mitigating hallucinations common in LLMs.

Contribution

The novel StreamProfile system combines incremental speech processing, evidence grounding, and a Chain-of-Thought pipeline for reliable psychological profile generation.

Findings

Accurately generates psychological profiles from teenager counseling speech.

Effectively prevents hallucinations in profile generation.

Demonstrates robustness in real-world clinical data.

Abstract

The psychological profile that structurally documents the case of a depression patient is essential for psychotherapy. Large language models can be applied to summarize the profiles from counseling speech, however, it may suffer from long-context forgetting and produce unverifiable hallucinations, due to overlong length of speech, multi-party interactions and unstructured chatting. Hereby, we propose a StreamProfile, a streaming framework that processes counseling speech incrementally, extracts evidences grounded from ASR transcriptions by storing it in a Hierarchical Evidence Memory, and then performs a Chain-of-Thought pipeline according to PM+ psychological intervention for clinical reasoning. The final profile is synthesized strictly from those evidences, making every claim traceable. Experiments on real-world teenager counseling speech have shown that the proposed StreamProfile system can accurately generate the profiles and prevent hallucination.