Work

From Atomic to Complex tasks: Cross-Tasking Improves Zero-Shot Argument Generation and Retrieval

Year: 2026

Type: conference-paper

Abstract: Cross-task generalization mimics human intelligence through the ability to perform tasks by recalling foundational skills acquired previously.In this paper, we argue that argument generation and argument retrieval are complex tasks that could leverage cross-tasking atomic argument mining and argument quality assessment tasks, even if there is no supervision.We empirically demonstrate the rationale behind our claim through the ArgLLM framework 1 , including a total of 18.9K instruction data using a multi-choice question-answering format, scaling up through multi-tasking and model merging, six natural language argumentation atomic tasks to four complex argument generation and argument retrieval tasks.Our results and analysis, using the backbone Mistral and Llama models, show that cross-tasking in zero-shot settings outperforms base models and is robust to varying strategies, tasks, and model sizes, offering a valuable trade-off between computational cost and task performance.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.1246

Authors: Lynda Tamine, Ahmed Rayane Kebir, Merveille Dona Codjo, Enzo Pasquies, Jose G Moreno

Institutions: Institut de Recherche en Informatique de Toulouse, Université de Toulouse

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Agence Nationale de la Recherche

Awards: General pUrpose dIalogue-based DigitAl iNformation acCEss, G4510828401, Artificial and Natural Intelligence Toulouse Institute