Filtering forecasts that are incoherent with their argumentative reasoning improved accuracy in human and LLM experiments, though users do not naturally follow the proposed coherence notion.
Evaluation of arguments in weighted bipolar graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Argumentatively Coherent Judgmental Forecasting
Filtering forecasts that are incoherent with their argumentative reasoning improved accuracy in human and LLM experiments, though users do not naturally follow the proposed coherence notion.