Develops a model-agnostic attribution score as the log-ratio of conditional response probabilities with and without a marginalized prompt token, derived via Bayes inversion of next-token distributions, and relates it to conditional entropies.
Jonathon Phillips and Carina Hahn and Peter Fontana and Amy Yates and Kristen K
3 Pith papers cite this work, alongside 212 external citations. Polarity classification is still indexing.
3
Pith papers citing it
212
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
unclear 1representative citing papers
RMCT matches the rate of target behaviors like bias-following across input perturbations to reduce sycophancy in LLMs while preserving verbalization of bias cues.
A systematic literature review defines self-explainability, proposes a taxonomy and levels framework, and reports that most approaches are conceptual with no standard evaluation method.
citing papers explorer
-
Probabilistic Attribution For Large Language Models
Develops a model-agnostic attribution score as the log-ratio of conditional response probabilities with and without a marginalized prompt token, derived via Bayes inversion of next-token distributions, and relates it to conditional entropies.
-
Consistency Training while Mitigating Obfuscation via Rate Matching
RMCT matches the rate of target behaviors like bias-following across input perturbations to reduce sycophancy in LLMs while preserving verbalization of bias cues.
-
Self-Explainability in Self-Adaptive and Self-Organising Systems: Status and Research Directions
A systematic literature review defines self-explainability, proposes a taxonomy and levels framework, and reports that most approaches are conceptual with no standard evaluation method.