REVIEW 8 cited by
Towards Emotional Support Dialog Systems
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats. Following reasonable procedures and using various support skills can help to effectively provide support. However, due to the lack of a well-designed task and corpora of effective emotional support conversations, research on building emotional support into dialog systems remains untouched. In this paper, we define the Emotional Support Conversation (ESC) 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. To ensure a corpus of high-quality conversations that provide examples of effective emotional support, we take extensive effort to design training tutorials for supporters and several mechanisms for quality control during data collection. Finally, we evaluate state-of-the-art dialog models with respect to the ability to provide emotional support. Our results show the importance of support strategies in providing effective emotional support and the utility of ESConv in training more emotional support systems.
Forward citations
Cited by 8 Pith papers
-
ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
A unified evaluation framework for proactive dialogue agents, built with 328 synthetic environments across six domains, shows that thinking modes improve target planning but not dialogue guidance in a 22-model comparison.
-
LLMs vs. Chinese Anime Enthusiasts: A Comparative Study on Emotionally Supportive Role-Playing
ChatAnime, a new emotionally supportive anime role-play benchmark, reports top LLMs outperforming human enthusiasts on role-playing and emotional support metrics while humans keep the diversity edge.
-
LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data
LEAP, an LLM-based library, automatically selects ML functions and writes SQL-like code to answer 92% of 120 social science queries over unstructured data on the first attempt, and 100% within three attempts.
-
Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues
LDPP automatically discovers latent dialogue policies from raw records and uses offline hierarchical reinforcement learning to plan in that latent space, outperforming strong baselines on proactive dialogue benchmarks.
-
Unlocking Speech Instruction Data Potential with Query Rewriting
A multi-LLM rewriting and multi-agent validation pipeline makes text-to-speech synthesized speech instruction data far more usable and improves downstream speech instruction following.
-
Spiritual-LLM : Gita Inspired Mental Health Therapy In the Era of LLMs
A Gita-based mental-health dialogue dataset helps small LLMs score higher on spirituality-oriented metrics, but the evaluation loop is largely self-referential.
-
SocialSim: Towards Socialized Simulation of Emotional Support Conversation
A new LLM-based pipeline, SocialSim, generates emotional support dialogues from a persona bank and cognitive reasoning chain, producing the SSConv corpus; a chatbot trained on SSConv outperforms crowdsourced-data base...
-
Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systems
Explicitly conditioning response generation on predicted socio-emotional label sequences yields only small, mixed quality gains over direct generation, and the claimed benefit is confounded by a 10-candidate reranking setup.
Discussion (0). Continue with ORCID to comment.