Pith. sign in

REVIEW 4 cited by

Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2408.11599 v1 pith:65DHTYOP submitted 2024-08-21 cs.CL cs.AI

Xinhao Chen , Chong Yang , Man Lan , Li Cai , Yang Chen , Tu Hu , Xinlin Zhuang , Aimin Zhou This is my paper · ORCID
classification cs.CLcs.AI
keywords empatheticgenerationapproachpromptresponsecause-awarechain-of-thoughtemotions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Empathetic response generation endows agents with the capability to comprehend dialogue contexts and react to expressed emotions. Previous works predominantly focus on leveraging the speaker's emotional labels, but ignore the importance of emotion cause reasoning in empathetic response generation, which hinders the model's capacity for further affective understanding and cognitive inference. In this paper, we propose a cause-aware empathetic generation approach by integrating emotions and causes through a well-designed Chain-of-Thought (CoT) prompt on Large Language Models (LLMs). Our approach can greatly promote LLMs' performance of empathy by instruction tuning and enhancing the role awareness of an empathetic listener in the prompt. Additionally, we propose to incorporate cause-oriented external knowledge from COMET into the prompt, which improves the diversity of generation and alleviates conflicts between internal and external knowledge at the same time. Experimental results on the benchmark dataset demonstrate that our approach on LLaMA-7b achieves state-of-the-art performance in both automatic and human evaluations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue

    cs.CL 2026-03 unverdicted novelty 6.0 of 10

    MICA mixes per-turn and whole-trajectory normalized reward signals to train emotional-support chatbots, outperforming GRPO and REINFORCE++ on EMPA, EQ-Bench, and EmoBench.

  2. Empathy Applicability Modeling for General Health Queries

    cs.CL 2026-01 conditional novelty 6.0 of 10

    General health queries can be labeled in advance for whether they call for emotional reactions or interpretive empathy, and classifiers trained on these labels beat simple baselines.

  3. Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness

    cs.CL 2025-10 conditional novelty 6.0 of 10

    PsySET measures emotion and personality steering in LLMs across prompting, fine-tuning, and representation engineering, finding prompts most effective overall and emotion-specific safety trade-offs (e.g., joy weakens ...

  4. Dynamic Commonsense Coordination for Empathetic Response Generation

    cs.CL 2026-07 conditional novelty 4.0 of 10

    DCC, a commonsense coordination framework with cross-source, filtering, and iterative-decoding modules, outperforms the CEM baseline on Empathetic-Dialogues emotion accuracy and diversity.

Pith tools