Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
Sequential integrated gradients: a simple but effective method for explaining language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Amortized optimization with policy gradients and graph knowledge selects informative word subsets to explain black-box DLM outputs.
citing papers explorer
-
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
-
Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets
Amortized optimization with policy gradients and graph knowledge selects informative word subsets to explain black-box DLM outputs.