Scholarlink

<p>A fundamental limitation of modern conversational AI is its limited capacity to demonstrate sustained empathy in long-form interactions. We propose <b>SCIRAG</b> (Semantic Context Improvisational Retrieval-Augmented Generation), a feedback-driven retrieval framework for adaptive empathic dialogue. It employs a dual-loop retrieval framework, iteratively optimizing a static counseling dataset through user metadata and feedback memory refinement. To enhance contextual alignment, we deploy retrieval adaptation, enabling the model to retain and leverage past conversational cues based on user preferences. When integrated with Mixtral-8x7B, SCIRAG improves human-rated empathic understanding by +1.26 points and empathic response by +1.00 point on the RoPE scale, while increasing acceptability by +7.66 points compared to a fine-tuned non-RAG baseline. Automatic evaluation further shows gains in semantic alignment (BERTScore-F1 +0.11) and fluency (perplexity reduced from 19.1 to 12.3). We also present <b>EMPATHIC</b>, a dataset of unscripted, therapeutic conversations. Unlike conventional datasets that contain only 2-4 dialogue turns per conversation, EMPATHIC provides extended conversational trajectories (50+ turns per session), allowing models to learn long-range coherence and empathic listening. The proposed dataset will be publicly released.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Semantic context improvisational retrieval-augmented generation for empathic conversational AI

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月26日

查看全文
  • Sharjeel Tahir,
  • Judith Johnson,
  • Jumana Abu-Khalaf,
  • Syed Afaq Ali Shah

摘要

A fundamental limitation of modern conversational AI is its limited capacity to demonstrate sustained empathy in long-form interactions. We propose SCIRAG (Semantic Context Improvisational Retrieval-Augmented Generation), a feedback-driven retrieval framework for adaptive empathic dialogue. It employs a dual-loop retrieval framework, iteratively optimizing a static counseling dataset through user metadata and feedback memory refinement. To enhance contextual alignment, we deploy retrieval adaptation, enabling the model to retain and leverage past conversational cues based on user preferences. When integrated with Mixtral-8x7B, SCIRAG improves human-rated empathic understanding by +1.26 points and empathic response by +1.00 point on the RoPE scale, while increasing acceptability by +7.66 points compared to a fine-tuned non-RAG baseline. Automatic evaluation further shows gains in semantic alignment (BERTScore-F1 +0.11) and fluency (perplexity reduced from 19.1 to 12.3). We also present EMPATHIC, a dataset of unscripted, therapeutic conversations. Unlike conventional datasets that contain only 2-4 dialogue turns per conversation, EMPATHIC provides extended conversational trajectories (50+ turns per session), allowing models to learn long-range coherence and empathic listening. The proposed dataset will be publicly released.