paper-with-me

Papers

Affective Flow Language Model for Emotional Support Conversation

2026-02-09 · Chenghui Zou, Ning Wang, Tiesunlong Shen, Luwei Xiao, Chuan Ma, Xiangpeng Li, Rui Mao, Erik Cambria arxiv

Large language models (LLMs) have been widely applied to emotional support conversation (ESC). However, complex multi-turn support remains challenging.This is because existing alignment schemes rely on sparse outcome-level signals, thus offering limited supervision for intermediate strategy decisions. To fill this gap, this paper proposes affective flow language model for emotional support conversation (AFlow), a framework that introduces fine-grained supervision on dialogue prefixes by modeling a continuous affective flow along multi-turn trajectories. AFlow can estimate intermediate utility over searched trajectories and learn preference-consistent strategy transitions. To improve strategy coherence and empathetic response quality, a subpath-level flow-balance objective is presented to propagate preference signals to intermediate states. Experiment results show consistent and significant improvements over competitive baselines in diverse emotional contexts. Remarkably, AFlow with a compact open-source backbone outperforms proprietary LMMs such as GPT-4o and Claude-3.5 on major ESC metrics. Our code is available at https://github.com/chz2025/AffectiveFlow.

📄 PDF Abstract BibTeX arXiv:2602.08826

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Affective Conversational Agents: Understanding Expectations and Personal Influences

2023-10-19 · Javier Hernandez, Jina Suh, Judith Amores, Kael Rowan 외

The rise of AI conversational agents has broadened opportunities to enhance human capabilities across various domains. As these agents become more prevalent, it is crucial to investigate the impact of different affective…

Affective Neural Response Generation

2017-09-12 · Nabiha Asghar, Pascal Poupart, Jesse Hoey, Xin Jiang 외

Existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue: its affective content. We take a step …

DecoderResponse GenerationWord Embeddings

Affect-LM: A Neural Language Model for Customizable Affective Text Generation

2017-04-22 · ACL 2017 7 · Sayan Ghosh, Mathieu Chollet, Eugene Laksana, Louis-Philippe Morency 외

Human verbal communication includes affective messages which are conveyed through use of emotionally colored words. There has been a lot of research in this direction but the problem of integrating state-of-the-art neura…

Language ModelingLanguage ModellingText Generation

TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent

2026-01-26 · Xingyu Sui, Yanyan Zhao, Yulin Hu, Jiahe Guo 외 arxiv

Emotional Support Conversation requires not only affective expression but also grounded instrumental support to provide trustworthy guidance. However, existing ESC systems and benchmarks largely focus on affective suppor…

Do You Feel Comfortable? Detecting Hidden Conversational Escalation in AI Chatbots

2025-12-05 · Jihyung Park, Saleh Afroogh, David Atkinson, Junfeng Jiao arxiv

Large Language Models (LLM) are increasingly integrated into everyday interactions, serving not only as information assistants but also as emotional companions. Even in the absence of explicit toxicity, repeated emotiona…