arXiv Computation and Language
All Learning Has an Emotional Basis, So Does Task-Oriented Dialogue
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Sep 10
Exposing Weaknesses in Emotion Recognition in Conversations
arXiv:2609.05806v1 Announce Type: new Abstract: Emotion Recognition in Conversations (ERC) aims to identify speakers' emotions in multi-turn dialogue. Accurate emotion recognition can support a wide...
arXiv Computation and Language
Sep 1
EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generation
arXiv:2607.23648v2 Announce Type: replace Abstract: Using large language models (LLMs) to assist psychological counseling is an important task in the field of natural language processing. The constru...
arXiv Computation and Language
Aug 25
ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents
arXiv:2608.21969v1 Announce Type: new Abstract: Humans have multiple levels of temporal abstractions on daily interaction and thinking, such as concept perception and strategic planning. Inspired by...
arXiv AI
Jul 17
Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decomposition
arXiv:2607. 14769v1 Announce Type: cross Abstract: Existing text summarization research has focused much on monologic information (e.
arXiv Computation and Language
Aug 28
Evaluating Language Models in Realistic Conversational Contexts
The paper introduces UPHELD, a large benchmark of human-to-human dialogues written by professional script writers, featuring realistic turn densities and over 36,000 per-turn human annotations. It evaluates existing automatic metrics and LLM-as-a-judge methods, finding them unreliable against expert human judgment. Using UPHELD, the authors develop a Mixture-of-Judges framework that improves correlation with human assessments by about 30%.
arXiv AI
Aug 3
Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
arXiv:2607. 27816v2 Announce Type: replace-cross Abstract: Role-playing agents (RPAs) have become one of the most important consumer applications of large language models.