# Fine-Tuning Large Audio-Language Models with LoRA for Precise Temporal Localization of Prolonged Exposure Therapy Elements

arXiv: https://arxiv.org/abs/2506.09707 · HTML: https://mlsanity.com/paper/2506.09707/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 18 of 18)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [FLAM: Frame-Wise Language-Audio Modeling](https://mlsanity.com/paper/2505.05335/) (2025)
- [Neural Topic Modeling of Psychotherapy Sessions](https://mlsanity.com/paper/2204.10189/) (2022)
- [Audio-free Prompt Tuning for Language-Audio Models](https://mlsanity.com/paper/2309.08357/) (2023)
- [Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations](https://mlsanity.com/paper/2504.13955/) (2025)
- [Automated Evaluation Of Psychotherapy Skills Using Speech And Language Technologies](https://mlsanity.com/paper/2102.11265/) (2021)
- [Privacy Sensitive Speech Analysis Using Federated Learning to Assess Depression](https://mlsanity.com/paper/2205.00111/) (2022)
- [COMPASS: Computational Mapping of Patient-Therapist Alliance Strategies with Language Modeling](https://mlsanity.com/paper/2402.14701/) (2024)
- [How Real Are Synthetic Therapy Conversations? Evaluating Fidelity in Prolonged Exposure Dialogues](https://mlsanity.com/paper/2504.21800/) (2025)
- [Feature Fusion Strategies for End-to-End Evaluation of Cognitive Behavior Therapy Sessions](https://mlsanity.com/paper/2005.07809/) (2020)
- [The Pursuit of Empathy: Evaluating Small Language Models for PTSD Dialogue Support](https://mlsanity.com/paper/2505.15065/) (2025)
- [Using Large Pre-Trained Models with Cross-Modal Attention for Multi-Modal Emotion Recognition](https://mlsanity.com/paper/2108.09669/) (2021)
- [Spatial Audio Processing with Large Language Model on Wearable Devices](https://mlsanity.com/paper/2504.08907/) (2025)
- [Towards Automated Real-time Evaluation in Text-based Counseling](https://mlsanity.com/paper/2203.03442/) (2022)
- [Characterizing Therapist's Speaking Style in Relation to Empathy in Psychotherapy](https://mlsanity.com/paper/2203.13127/) (2022)

## Built on by (most cited first, 3 of 3)

- [Exploring Fine-Tuning of Large Audio Language Models for Spoken Language Understanding under Limited Speech Data](https://mlsanity.com/paper/2509.15389/) (2025)
- [Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs](https://mlsanity.com/paper/2604.16659/) (2026)
- [AI Safety Training Can be Clinically Harmful](https://mlsanity.com/paper/2604.23445/) (2026)

## Abstract (arXiv)

Prolonged Exposure (PE) therapy is an effective treatment for post-traumatic stress disorder (PTSD), but evaluating therapist fidelity remains labor-intensive due to the need for manual review of session recordings. We present a method for the automatic temporal localization of key PE fidelity elements, identifying their start and stop times, directly from session audio and transcripts. Our approach fine-tunes a large pre-trained audio-language model, Qwen2-Audio, using Low-Rank Adaptation (LoRA) to process focused 30-second windows of audio-transcript input. Fidelity labels for three core protocol phases, therapist orientation (P1), imaginal exposure (P2), and post-imaginal processing (P3), are generated via LLM-based prompting and verified by trained raters. The model is trained to predict normalized boundary offsets using soft supervision guided by task-specific prompts. On a dataset of 308 real PE sessions, our best configuration (LoRA rank 8, 30s windows) achieves a mean absolute error (MAE) of 5.3s across tasks, within typical rater tolerance for timestamp review, enabling practical fidelity QC. We further analyze the effects of window size and LoRA rank, highlighting the importance of context granularity and model adaptation. This work introduces a privacy-preserving, scalable framework for fidelity tracking in PE therapy, with potential to support clinician training, supervision, and quality assurance.