BiGraph-Diffuse: A Bidirectional Diffusion Language Model with Graph-Structured Retrieval For Mental Health Counseling
On the map: Diffusion models → Discrete and text diffusion
Abstract (arXiv)
Mental health disorders affect hundreds of millions of people around the world, yet access to professional counseling remains severely limited. AI-powered dialogue systems offer a scalable alternative, but existing models face two fundamental challenges. First, they lack the bidirectional understanding needed to capture the layered nature of emotional expression, particularly in cases of progressive disclosure, where clients often present symptoms at the surface-level while concealing deeper trauma. Autoregressive (AR) models process information sequentially and cannot revise early interpretations when new evidence emerges later in the conversation. Second, they fail to effectively incorporate the relational knowledge that underlies clinical reasoning. In this paper, we propose BiGraph-Diffuse, the first large-scale diffusion language model tailored for the counseling domain. We further introduce BiGraph-RAG, a relation-free graph-structured retrieval strategy that relies only on lightweight entity extraction and semantic linking. This design preserves inferential pathways from observable symptoms to potential underlying causes, while incurring zero LLM token cost during indexing. Importantly, these two modules are not merely combined but mutually reinforcing. The diffusion model provides a holistic bidirectional context, enabling the system to defer premature judgments during progressive disclosure. Meanwhile, graph-based retrieval captures the structured interconnections of clinical knowledge. Extensive experiments demonstrate the effectiveness of BiGraph-Diffuse, and we further provide a solid theoretical analysis to support its design.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 30 of its 38 references that are in the map. First posted on arXiv 25 Aug 2026.
Builds on
30 of 38 references.
Closest ancestors · 3
Same direction, newest first
- 2025Large Language Diffusion Models14 Feb
- 2024Simple and Effective Masked Diffusion Language Models11 Jun
- 2024Simplified and Generalized Masked Diffusion for Discrete Data6 Jun
Other references · 27
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2024GPT-4o System Cardcited by 4,588
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 407
- 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
- 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
- 2023SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversationscited by 110
- 2021PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Supportcited by 92
- 2024CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counselingcited by 89
- 2023MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Modelscited by 63
- 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corporacited by 49
- 2023SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Supportcited by 46
15 more
- 2024ESCoT: Towards Interpretable Emotional Support Dialogue Systemscited by 46
- 2023ChatCounselor: A Large Language Models for Mental Health Supportcited by 44
- 2024PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counselingcited by 38
- 2023Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Healthcited by 25
- 2024Do Large Language Models Align with Core Mental Health Counseling Competencies?cited by 19
- 2025When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluationcited by 19
- 2025Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counselingcited by 18
- 2023Challenges of Large Language Models for Mental Health Counselingcited by 17
- 2023Rethinking Large Language Models in Mental Health Applicationscited by 16
- 2024MDD-5k: A New Diagnostic Conversation Dataset for Mental Disorders Synthesized via Neuro-Symbolic LLM Agentscited by 16
- 2025KokoroChat: A Japanese Psychological Counseling Dialogue Dataset Collected via Role-Playing by Trained Counselorscited by 13
- 2025CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Explorationcited by 11
- 2025Psi-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedbackcited by 10
- 2025MCTSr-Zero: Self-Reflective Psychological Counseling Dialogues Generation via Principles and Adaptive Explorationcited by 5
- 2026PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generationcited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Reasoning Over Recall: Evaluating the Efficacy of Generalist Architectures vs. Specialized Fine-Tunes in RAG-Based Mental Health Dialogue Systems
- 2025Psy-Insight: Explainable Multi-turn Bilingual Dataset for Mental Health Counseling
- 2024Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization
- 2026InsightFlow: LLM-Driven Synthesis of Patient Narratives for Mental Health into Causal Models
- 2025MindEval: Benchmarking Language Models on Multi-turn Mental Health Support
- 2024Conversational Topic Recommendation in Counseling and Psychotherapy with Decision Transformer and Large Language Models
- 2025Psy-Copilot: Visual Chain of Thought for Counseling
- 2026Towards Privacy-Preserving Mental Health Support with Large Language Models