MOCC-R1: Reinforcing Reasoning-Response Consistency for Multimodal Counselor Response Generation

• URL: http://arxiv.org/abs/2609.17180v1
• Date: Tue, 15 Sep 2026 13:41:19 GMT
• Title: MOCC-R1: Reinforcing Reasoning-Response Consistency for Multimodal Counselor Response Generation
• Abstract summary: Multimodal counselor response generation (MCRG) aims to generate an appropriate counselor response from multimodal dialogue histories.<n>Existing datasets rarely capture sustained, human-recorded counseling interactions conducted by qualified counselors.<n>We introduce MOCC, a multimodal counseling conversation corpus containing over 200 hours of interactions involving 154 credential-verified counselors.
• Score: 38.53210416623622
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal counselor response generation (MCRG) aims to generate an appropriate counselor response from multimodal dialogue histories. Progress is limited by two gaps: first, existing datasets rarely capture sustained, human-recorded counseling interactions conducted by qualified counselors; Second, existing methods do not explicitly optimize consistency between counseling reasoning and the generated response, potentially undermining the reliability of MCRG systems. Thus, we introduce MOCC, a multimodal counseling conversation corpus containing over 200 hours of interactions involving 154 credential-verified counselors. Based on MOCC, we propose MOCC-R1, a two-stage framework for optimizing reasoning-response consistency. Cold-start supervised fine-tuning trains the model to generate a structured trajectory consisting of client-state understanding, a response intent that links a counseling principle to a planned action, and the final response. Reinforcement learning (RL) then rewards grounded plan coherence and plan execution, encouraging the inferred state and plan to be supported by the dialogue context and the response to realize that plan. Experiments demonstrate the effectiveness of the proposed MOCC-R1.

Related papers

• Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning [137.33138614095435]
  Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models.<n>Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval.<n>We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions.
  arXiv  Detail & Related papers  (2025-11-12T08:29:39Z)
• CATCH: A Novel Data Synthesis Framework for High Therapy Fidelity and Memory-Driven Planning Chain of Thought in AI Counseling [33.31877691538151]
  CATCH is a novel data synthesis framework designed to address these challenges.<n>To improve therapy fidelity, we introduce the Progressive Dialogue Synthesis strategy.<n>To capture decision-making rationale behind each response, we propose the Memory-Driven Thinking pattern.
  arXiv  Detail & Related papers  (2025-09-30T03:44:00Z)
• Planning Like Human: A Dual-process Framework for Dialogue Planning [31.995557540062553]
  We propose the Dual-Process Dialogue Planning framework to enhance dialogue planning in Large Language Models (LLMs) Inspired by the dualprocess theory in psychology, we propose the framework, which embodies two modes of thinking: intuitive (fast) and analytical (slow) Our empirical evaluations affirm DPDP's superiority in achieving both high-quality dialogues and operational efficiency, outpacing existing methods.
  arXiv  Detail & Related papers  (2024-06-08T06:52:47Z)
• JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning [53.83063435640911]
  Dialogue policy learning (DPL) is a crucial component of dialogue modelling. We introduce a novel framework, JoTR, to generate flexible dialogue actions. Unlike traditional methods, JoTR formulates a word-level policy that allows for a more dynamic and adaptable dialogue action generation.
  arXiv  Detail & Related papers  (2023-09-01T03:19:53Z)
• EM Pre-training for Multi-party Dialogue Response Generation [86.25289241604199]
  In multi-party dialogues, the addressee of a response utterance should be specified before it is generated. We propose an Expectation-Maximization (EM) approach that iteratively performs the expectation steps to generate addressee labels.
  arXiv  Detail & Related papers  (2023-05-21T09:22:41Z)
• Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems [5.012848165681843]
  We propose a concept-guided non-autoregressive model (CG-nAR) for open-domain dialogue generation. The proposed model comprises a multi-concept planning module that learns to identify multiple associated concepts from a concept graph. The experimental results on two public datasets show that CG-nAR can produce diverse and coherent responses.
  arXiv  Detail & Related papers  (2021-09-09T08:00:44Z)
• Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues [88.73739515457116]
  We introduce four self-supervised tasks including next session prediction, utterance restoration, incoherence detection and consistency discrimination. We jointly train the PLM-based response selection model with these auxiliary tasks in a multi-task manner. Experiment results indicate that the proposed auxiliary self-supervised tasks bring significant improvement for multi-turn response selection.
  arXiv  Detail & Related papers  (2020-09-14T08:44:46Z)
• Multi-Domain Dialogue Acts and Response Co-Generation [34.27525685962274]
  We propose a neural co-generation model that generates dialogue acts and responses concurrently. Our model achieves very favorable improvement over several state-of-the-art models in both automatic and human evaluations.
  arXiv  Detail & Related papers  (2020-04-26T12:21:17Z)
• Dialogue-Based Relation Extraction [53.2896545819799]
  We present the first human-annotated dialogue-based relation extraction (RE) dataset DialogRE. We argue that speaker-related information plays a critical role in the proposed task, based on an analysis of similarities and differences between dialogue-based and traditional RE tasks. Experimental results demonstrate that a speaker-aware extension on the best-performing model leads to gains in both the standard and conversational evaluation settings.
  arXiv  Detail & Related papers  (2020-04-17T03:51:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.