A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
A multimodal framework for automated teaching quality assessment of one-to-many online instruction videos
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
MAG-VLAQ fuses multi-modal ground and aerial data via ODE-conditioned vector-of-locally-aggregated-queries to nearly double recall@1 on aerial-ground place recognition benchmarks.
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
TFMPathy applies tabular foundation models to summary statistics of visual features for subject-generalizable empathy detection under strong privacy constraints, with improved cross-subject performance on a public benchmark.
citing papers explorer
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
MAG-VLAQ: Multi-modal Aerial-Ground Query Aggregation for Cross-View Place Recognition
MAG-VLAQ fuses multi-modal ground and aerial data via ODE-conditioned vector-of-locally-aggregated-queries to nearly double recall@1 on aerial-ground place recognition benchmarks.
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
-
Privacy-Preserving Empathy Detection in Video Interactions
TFMPathy applies tabular foundation models to summary statistics of visual features for subject-generalizable empathy detection under strong privacy constraints, with improved cross-subject performance on a public benchmark.
- Differentiable Learning of Lifted Action Schemas for Classical Planning