Large language models display the identifiable victim effect at roughly twice the human baseline, strongly amplified by instruction tuning and chain-of-thought prompting but inverted by reasoning-specialized models.
Advances in neural information processing systems35, 27730–27744 (2022)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
STaR-DRO applies momentum-smoothed Tsallis reweighting to focus learning on hard groups in structured prediction, yielding F1 gains on clinical label extraction.
AIGC creators match HGC engagement via high-volume production despite consumer preference for HGC, with algorithms moderating the effect.
citing papers explorer
-
Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models
Large language models display the identifiable victim effect at roughly twice the human baseline, strongly amplified by instruction tuning and chain-of-thought prompting but inverted by reasoning-specialized models.
-
STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction
STaR-DRO applies momentum-smoothed Tsallis reweighting to focus learning on hard groups in structured prediction, yielding F1 gains on clinical label extraction.
-
Scale over Preference: The Impact of AI-Generated Content on Online Content Ecology
AIGC creators match HGC engagement via high-volume production despite consumer preference for HGC, with algorithms moderating the effect.