PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
Computational Linguis- tics 45(4), 765–818 (Dec 2019)
5 Pith papers cite this work, alongside 384 external citations. Polarity classification is still indexing.
5
Pith papers citing it
384
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
A quantitative bipolar argumentation framework with five metrics is proposed to evaluate LLM debate summaries by comparing argument structures extracted from source debates and their summaries.
TruthSplit is an interactive system that extracts claims from arguments and uses three-layer NLI plus LLM reasoning conditioned on structured worldview profiles to surface perspective-specific conditional validity, value conflicts, and assumption gaps.
CAF-Gen uses an iterative multi-agent creator-reviewer process to enrich shallow argument mining outputs into structurally richer CAF-compliant models with claimed improvements over single-pass generation.
Trait-conditioned LLM prosecution/defense teams in a simulated courtroom show heterogeneous traits and an RL Trait Orchestrator outperforming static homogeneous teams across thousands of synthetic trials.
citing papers explorer
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
Evaluating LLM-Driven Summarisation of Parliamentary Debates with Computational Argumentation
A quantitative bipolar argumentation framework with five metrics is proposed to evaluate LLM debate summaries by comparing argument structures extracted from source debates and their summaries.
-
TruthSplit: Operationalizing Conditional Validity in Arguments Through Multi-Perspective Reasoning
TruthSplit is an interactive system that extracts claims from arguments and uses three-layer NLI plus LLM reasoning conditioned on structured worldview profiles to surface perspective-specific conditional validity, value conflicts, and assumption gaps.
-
CAF-Gen: A Multi-Agent System for Enriching Argumentation Structures
CAF-Gen uses an iterative multi-agent creator-reviewer process to enrich shallow argument mining outputs into structurally richer CAF-compliant models with claimed improvements over single-pass generation.
-
Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argumentation
Trait-conditioned LLM prosecution/defense teams in a simulated courtroom show heterogeneous traits and an RL Trait Orchestrator outperforming static homogeneous teams across thousands of synthetic trials.