Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation
- URL: http://arxiv.org/abs/2402.13211v2
- Date: Wed, 5 Jun 2024 13:39:59 GMT
- Title: Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation
- Authors: Dongjin Kang, Sunghwan Kim, Taeyoon Kwon, Seungjun Moon, Hyunsouk Cho, Youngjae Yu, Dongha Lee, Jinyoung Yeo,
- Abstract summary: This work initially analyzes the results of large language models (LLMs) on ESConv.
We observe that exhibiting high preference for specific strategies hinders effective emotional support.
Our findings emphasize that (1) low preference for specific strategies hinders the progress of emotional support, (2) external assistance helps reduce preference bias, and (3) existing LLMs alone cannot become good emotional supporters.
- Score: 28.74445806009475
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Emotional Support Conversation (ESC) is a task aimed at alleviating individuals' emotional distress through daily conversation. Given its inherent complexity and non-intuitive nature, ESConv dataset incorporates support strategies to facilitate the generation of appropriate responses. Recently, despite the remarkable conversational ability of large language models (LLMs), previous studies have suggested that they often struggle with providing useful emotional support. Hence, this work initially analyzes the results of LLMs on ESConv, revealing challenges in selecting the correct strategy and a notable preference for a specific strategy. Motivated by these, we explore the impact of the inherent preference in LLMs on providing emotional support, and consequently, we observe that exhibiting high preference for specific strategies hinders effective emotional support, aggravating its robustness in predicting the appropriate strategy. Moreover, we conduct a methodological study to offer insights into the necessary approaches for LLMs to serve as proficient emotional supporters. Our findings emphasize that (1) low preference for specific strategies hinders the progress of emotional support, (2) external assistance helps reduce preference bias, and (3) existing LLMs alone cannot become good emotional supporters. These insights suggest promising avenues for future research to enhance the emotional intelligence of LLMs.
Related papers
- The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional
Supporters for Queer Youth [14.751539420563752]
This paper aims to explore the potential of Large Language Models to revolutionize emotional support for queers.
We develop a novel ten-question scale that is inspired by psychological standards and expert input.
We find that LLM responses are supportive and inclusive, outscoring humans.
However, they tend to be generic, not empathetic enough, and lack personalization, resulting in nonreliable and potentially harmful advice.
arXiv Detail & Related papers (2024-02-19T06:54:55Z) - Steering Conversational Large Language Models for Long Emotional Support
Conversations [5.601537787608725]
We introduce the Strategy-Relevant Attention metric, a model-agnostic measure designed to evaluate the effectiveness of large language models (LLMs) in adhering to strategic prompts in emotional support contexts.
Our findings reveal that the application of SRA-informed prompts leads to enhanced strategic adherence, resulting in conversations that more reliably exhibit the desired emotional support strategies over longer conversations.
arXiv Detail & Related papers (2024-02-16T05:03:01Z) - CauESC: A Causal Aware Model for Emotional Support Conversation [79.4451588204647]
Existing approaches ignore the emotion causes of the distress.
They focus on the seeker's own mental state rather than the emotional dynamics during interaction between speakers.
We propose a novel framework CauESC, which firstly recognizes the emotion causes of the distress, as well as the emotion effects triggered by the causes.
arXiv Detail & Related papers (2024-01-31T11:30:24Z) - Enhancing Emotional Generation Capability of Large Language Models via
Emotional Chain-of-Thought [53.1230874584344]
Large Language Models (LLMs) have shown remarkable performance in various emotion recognition tasks.
We propose the Emotional Chain-of-Thought (ECoT) to enhance the performance of LLMs on various emotional generation tasks.
arXiv Detail & Related papers (2024-01-12T16:42:10Z) - Building Emotional Support Chatbots in the Era of LLMs [64.06811786616471]
We introduce an innovative methodology that synthesizes human insights with the computational prowess of Large Language Models (LLMs)
By utilizing the in-context learning potential of ChatGPT, we generate an ExTensible Emotional Support dialogue dataset, named ExTES.
Following this, we deploy advanced tuning techniques on the LLaMA model, examining the impact of diverse training strategies, ultimately yielding an LLM meticulously optimized for emotional support interactions.
arXiv Detail & Related papers (2023-08-17T10:49:18Z) - Facilitating Multi-turn Emotional Support Conversation with Positive
Emotion Elicitation: A Reinforcement Learning Approach [58.88422314998018]
Emotional support conversation (ESC) aims to provide emotional support (ES) to improve one's mental state.
Existing works stay at fitting grounded responses and responding strategies which ignore the effect on ES and lack explicit goals to guide emotional positive transition.
We introduce a new paradigm to formalize multi-turn ESC as a process of positive emotion elicitation.
arXiv Detail & Related papers (2023-07-16T09:58:44Z) - Improving Multi-turn Emotional Support Dialogue Generation with
Lookahead Strategy Planning [81.79431311952656]
We propose a novel system MultiESC to provide Emotional Support.
For strategy planning, we propose lookaheads to estimate the future user feedback after using particular strategies.
For user state modeling, MultiESC focuses on capturing users' subtle emotional expressions and understanding their emotion causes.
arXiv Detail & Related papers (2022-10-09T12:23:47Z) - Towards Emotional Support Dialog Systems [61.58828606097423]
We define the Emotional Support Conversation task and propose an ESC Framework, which is grounded on the Helping Skills Theory.
We construct an Emotion Support Conversation dataset (ESConv) with rich annotation (especially support strategy) in a help-seeker and supporter mode.
We evaluate state-of-the-art dialog models with respect to the ability to provide emotional support.
arXiv Detail & Related papers (2021-06-02T13:30:43Z)
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.