A training-free method improves epistemic faithfulness of LLM textual explanations by guiding generation with attribution-based attention interventions.
Attnlrp: attention-aware layer-wise relevance propagation for transformers
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.
An attribution-based continual learning framework for LLMs modulates per-parameter gradients using task-specific importance scores to reduce forgetting of prior tasks.
citing papers explorer
-
Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance
A training-free method improves epistemic faithfulness of LLM textual explanations by guiding generation with attribution-based attention interventions.
-
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.
-
Attribution-Guided Continual Learning for Large Language Models
An attribution-based continual learning framework for LLMs modulates per-parameter gradients using task-specific importance scores to reduce forgetting of prior tasks.