Papers with theoretical model

4 papers
Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights (2022.tacl-1)

Copied to clipboard

Challenge: a robust dialogue agent cannot assume a cooperative conversational counterpart when deployed in the wild.
Approach: They propose a theoretical model for identifying non-cooperative interlocutors . they use reinforcement learning to implement multiple communication strategies .
Outcome: The proposed model is validated by using reinforcement learning to implement multiple communication strategies.
Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to solving complex tasks with large language models (LLMs) fail to decompose tasks accurately or execute subtasks effectively.
Approach: They propose a Chain-of-Learning (CoL) paradigm that highlights task dependencies on specific capability items, further broken down into their constituent knowledge and skill components.
Outcome: The proposed model improves Yi-1.5-9B and Llama3-Chinese-8B for legal tasks by 45.00% and 24.50% on different domains.
Abstractive Text Summarization Based on Deep Learning and Semantic Content Generalization (P19-1)

Copied to clipboard

Challenge: Abstractive text summarization is a demanding, time expensive and generally laborious task.
Approach: They propose a framework for enhancing abstractive text summarization using deep learning techniques and semantic data transformations.
Outcome: The proposed method is evaluated on two popular datasets with encouraging results.
KODIS: A Multicultural Dispute Resolution Dialogue Corpus (2025.naacl-long)

Copied to clipboard

Challenge: KODIS is a dyadic dispute resolution corpus containing thousands of dialogues from over 75 countries.
Approach: They propose to use a dyadic dispute resolution corpus to examine how conflicts escalate through conversation rather than deal-making.
Outcome: The proposed corpus contains thousands of dialogues from over 75 countries.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations