Proposes SCSuff metric for evaluating LLM explanation sufficiency via model-generated alternative inputs, showing explanations are typically insufficient and predictable from hidden states.
editor =
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
Pruning attention layers in five LLMs across eight datasets maintains accuracy but degrades faithfulness and calibration.
CERA fine-tunes a dense retriever with triplet contrastive learning plus attention alignment to human rationales, claiming better retrieval effectiveness and faithfulness on clinical trial reports than Contriever and standard hard-negative baselines.
PrimeFacts extracts decontextualized premises from fact-check articles, raising evidence retrieval MRR by up to 30% and verdict prediction Macro-F1 by 10-20 points over baselines.
EPPC-OASIS combines ontology-aware fine-tuning via Wasserstein alignment with structured inference refinement to extract EPPC codes from secure messages, reporting 77.13% Code+Sub-code F1 and 63.83% Triplet F1 with small gains over supervised fine-tuning baselines.
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.
An off-the-shelf LLM prompted on tokenized Modbus traffic from public ICS datasets matches supervised baselines in normal-versus-critical classification accuracy while generating token-grounded audit records without any model updates.
citing papers explorer
-
What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs
Proposes SCSuff metric for evaluating LLM explanation sufficiency via model-generated alternative inputs, showing explanations are typically insufficient and predictable from hidden states.
-
Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration
Pruning attention layers in five LLMs across eight datasets maintains accuracy but degrades faithfulness and calibration.
-
Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
CERA fine-tunes a dense retriever with triplet contrastive learning plus attention alignment to human rationales, claiming better retrieval effectiveness and faithfulness on clinical trial reports than Contriever and standard hard-negative baselines.
-
From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence
PrimeFacts extracts decontextualized premises from fact-check articles, raising evidence retrieval MRR by up to 30% and verdict prediction Macro-F1 by 10-20 points over baselines.
-
EPPC-OASIS: Ontology-Aware Adaptation and Structured Inference Refinement for Electronic Patient-Provider Communication Mining in Secure Messages
EPPC-OASIS combines ontology-aware fine-tuning via Wasserstein alignment with structured inference refinement to extract EPPC codes from secure messages, reporting 77.13% Code+Sub-code F1 and 63.83% Triplet F1 with small gains over supervised fine-tuning baselines.
-
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.
-
Large Language Models as Explainable Cyberattack Detectors for Energy Industrial Control Systems
An off-the-shelf LLM prompted on tokenized Modbus traffic from public ICS datasets matches supervised baselines in normal-versus-critical classification accuracy while generating token-grounded audit records without any model updates.