# Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols

arXiv: https://arxiv.org/abs/2608.31014 · HTML: https://mlsanity.com/paper/2608.31014/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 9 of 9)

- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models](https://mlsanity.com/paper/2505.21523/) (2025)
- [MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow](https://mlsanity.com/paper/2503.18968/) (2025)
- [Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2502.06872/) (2025)
- [Speech as a Multimodal Digital Phenotype for Multi-Task LLM-based Mental Health Prediction](https://mlsanity.com/paper/2505.23822/) (2025)
- [MentalBench: A DSM-Grounded Benchmark for Evaluating Psychiatric Diagnostic Capability of Large Language Models](https://mlsanity.com/paper/2602.12871/) (2026)
- [Schema-Adaptive Tabular Representation Learning with LLMs for Generalizable Multimodal Clinical Reasoning](https://mlsanity.com/paper/2604.11835/) (2026)

## Abstract (arXiv)

Computational mental health screening using multimodal speech and text has shown great promise. However, existing models often assume all clinical speech protocols carry equivalent evidentiary validity. In reality, heterogeneous protocols, from free interviews to fixed reading tasks, support fundamentally different evidence. Forcing uniform reasoning flattens these boundaries, causing models to hallucinate symptoms from irrelevant text or overclaim support. Even advanced long chain-of-thought LLMs fail to resolve this issue, as free-form reasoning can exacerbate boundary violations. To address this, we reformulate multimodal screening as an evidence-bounded reasoning problem. We introduce the Evidence Package Benchmark, integrating 1,870 packages across six heterogeneous sources with explicit modality masks and evidence permissions. We further propose EviBound, a protocol-aware evidence control framework. Unlike direct LLM prompting, EviBound uses a profile-aware planner to restrict reasoning scope, orchestrates evidence tools via five-way acoustic consensus, and enforces a boundary critic to suppress unsupported claims. Empirical results show EviBound achieves a held-out test Depression AUROC of 0.8658, exceeding the strongest direct omni-modal baseline by +0.0811 AUROC while maintaining zero claim violations. Our work moves beyond unconstrained accuracy toward evidence-consistent, protocol-aware systems for safer clinical NLP research.