A two-stage LLM explainer-verifier framework with iterative refeed improves faithfulness and accessibility of XAI explanations, as shown in experiments across five techniques and three LLM families, with EPR analysis indicating progressive stabilization.
LLMs for XAI: Future directions for explaining explanations
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
A conjecture-then-validate method lets LLMs convert opaque lexical cues from deceptive-review classifiers into interpretable language phenomena that are empirically grounded and more predictive than direct LLM outputs.
High-quality LLM explanations for time-series forecasts boost confidence without improving accuracy across five tasks, functioning as trust heuristics rather than decision aids.
NEURON integrates SNOMED CT, ML, and RAG LLM to raise AUC from 0.74-0.77 to 0.84-0.88 and human-aligned explainability scores from 0.50 to 0.85 on MIMIC-IV acute heart failure data.
citing papers explorer
-
A Two-Stage LLM Framework for Accessible and Verified XAI Explanations
A two-stage LLM explainer-verifier framework with iterative refeed improves faithfulness and accessibility of XAI explanations, as shown in experiments across five techniques and three LLM families, with EPR analysis indicating progressive stabilization.
-
Why is "Chicago" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues
A conjecture-then-validate method lets LLMs convert opaque lexical cues from deceptive-review classifiers into interpretable language phenomena that are empirically grounded and more predictive than direct LLM outputs.
-
Quality Without Usefulness: LLM-Generated XAI Narratives as Trust Heuristics Rather Than Decision Aids
High-quality LLM explanations for time-series forecasts boost confidence without improving accuracy across five tasks, functioning as trust heuristics rather than decision aids.
-
NEURON: A Neuro-symbolic System for Grounded Clinical Explainability
NEURON integrates SNOMED CT, ML, and RAG LLM to raise AUC from 0.74-0.77 to 0.84-0.88 and human-aligned explainability scores from 0.50 to 0.85 on MIMIC-IV acute heart failure data.