Atom-wise selective abstraction—replacing low-confidence factual claims with higher-confidence, less specific versions—improves the risk-coverage trade-off in long-form generation by up to 27.73% AURC over claim removal.
Semantic information.British Journal for the Philosophy of Science, 4(14):147–157, 1953
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
Atom-wise selective abstraction—replacing low-confidence factual claims with higher-confidence, less specific versions—improves the risk-coverage trade-off in long-form generation by up to 27.73% AURC over claim removal.