Entity · paper

Generation or Judgement? A Paradigm Perspective on LLM-Based Emotion-Cause Pair Extraction in Conversation

paperactiveprovisionalgeneration-or-judgement-a-paradigm-perspective-on-llm-based-emotion-cause-pair-extraction-in-conversation-6db210b0·1 events·first seen 25h ago

Aliases: Generation or Judgement? A Paradigm Perspective on LLM-Based Emotion-Cause Pair Extraction in Conversation

More like this (12)

Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs From Self to Other: Evaluating Demographic Perspective-Taking in LLM Hate Speech Annotation Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation Judgement-of-Learning Generative Skill Composition for LLM Agents Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer From Representations to Behaviors: Exploring the Person-Situation-Behavior Triad in LLMs Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs Dynamic Commonsense Coordination for Empathetic Response Generation Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias

Recent events (1)

4arXiv · cs.CL·25h ago·source ↗

Pair-level judgement outperforms dialogue-level generation for LLM emotion-cause extraction

A new arXiv paper investigates how task formulation affects LLM performance on emotion-cause pair extraction in conversation (ECPEC), finding that pair-level judgement consistently outperforms dialogue-level generation across 18 controlled comparisons. The authors show LLMs can recognize 92.7–98.1% of emotion-cause relations when queried explicitly but struggle to discover complete pair sets autonomously. They introduce an auxiliary retriever targeting ambiguous boundary cases, achieving F1 improvements of 0.50–1.46 points across three datasets at only 1.49x inference cost. The findings have broader implications for how task decomposition and candidate scoping affect LLM utilization in structured extraction tasks.

Evaluation and Benchmarking Generation or Judgement? A Paradigm Perspective on LLM-Based Emotion-Cause Pair Extraction in Conversation