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.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
ODRPO decomposes discrete rewards into ordinal binary indicators to create robust, variance-aware advantage estimators for noisy RLAIF in LLM alignment.
TaskLens uses LLMs to generate task-specific scaffolded interfaces that reduce perceived workload and improve performance and concept learning for novices using professional 3D software.
QuickLAP fuses LLM-extracted language observations with physical feedback in a closed-form Bayesian update to cut reward learning error by over 70% in a driving simulator and improve user preference in a 15-person study.
Machine learning on task-based EEG outperforms resting-state for ADHD classification, while diffusion and structural MRI link white-matter integrity and grey-matter volume in fronto-parietal regions to effort-reward parameters and subclinical apathy.
Fine-tuned foundation models produce reliable MSK MRI biomarkers that support workload-reducing triage and calibrated 48-month prediction of knee replacement and incident OA.
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.
-
ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization
ODRPO decomposes discrete rewards into ordinal binary indicators to create robust, variance-aware advantage estimators for noisy RLAIF in LLM alignment.
-
TaskLens: Generating Task-Conditioned Scaffolded Interfaces for Learning Professional Creative Software
TaskLens uses LLMs to generate task-specific scaffolded interfaces that reduce perceived workload and improve performance and concept learning for novices using professional 3D software.
-
QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents
QuickLAP fuses LLM-extracted language observations with physical feedback in a closed-form Bayesian update to cut reward learning error by over 70% in a driving simulator and improve user preference in a 15-person study.
-
Machine learning approaches to uncover the neural mechanisms of motivated behaviour: from ADHD to individual differences in effort and reward sensitivity
Machine learning on task-based EEG outperforms resting-state for ADHD classification, while diffusion and structural MRI link white-matter integrity and grey-matter volume in fronto-parietal regions to effort-reward parameters and subclinical apathy.
-
Clinical utility of foundation models in musculoskeletal MRI for biomarker fidelity and predictive outcomes
Fine-tuned foundation models produce reliable MSK MRI biomarkers that support workload-reducing triage and calibrated 48-month prediction of knee replacement and incident OA.