SOTAVerified

Explanation Generation

Papers

Showing 76100 of 235 papers

TitleStatusHype
Explainable Debugger for Black-box Machine Learning ModelsCode0
LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language InferenceCode0
Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language ExplanationsCode0
IndMask: Inductive Explanation for Multivariate Time Series Black-Box ModelsCode0
GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge GraphsCode0
A Framework for Learning Ante-hoc Explainable Models via ConceptsCode0
Explaining Veracity Predictions with Evidence Summarization: A Multi-Task Model ApproachCode0
Explainable Agency by Revealing Suboptimality in Child-Robot Learning ScenariosCode0
Generating High-Quality Explanations for Navigation in Partially-Revealed EnvironmentsCode0
RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-CheckingCode0
RecExplainer: Aligning Large Language Models for Explaining Recommendation ModelsCode0
Generating High-Quality Explanations for Navigation in Partially-Revealed EnvironmentsCode0
Explanation Regeneration via Information BottleneckCode0
RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine ConflictCode0
Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement LearningCode0
Multimodal Coherent Explanation Generation of Robot FailuresCode0
Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation GenerationCode0
ExPUNations: Augmenting Puns with Keywords and ExplanationsCode0
Enriching Visual with Verbal Explanations for Relational Concepts -- Combining LIME with Aleph0
Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes0
Enhancing Emotion Prediction in News Headlines: Insights from ChatGPT and Seq2Seq Models for Free-Text Generation0
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images0
E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning0
E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning0
EGCR: Explanation Generation for Conversational Recommendation0
Show:102550
← PrevPage 4 of 10Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1VLIS (Lynx)Accuracy80Unverified
2VLIS (LLaVA)Accuracy73Unverified
3Ground-truth Caption -> GPT3 (Oracle)Human (%)68Unverified
4Predicted Caption -> GPT3Human (%)33Unverified
5BLIP2 FlanT5-XXL (Fine-tuned)Human (%)27Unverified
6BLIP2 FlanT5-XL (Fine-tuned)Human (%)15Unverified
7BLIP2 FlanT5-XXL (Zero-shot)Human (%)0Unverified
#ModelMetricClaimedVerifiedStatus
1PJ-XB487.4Unverified
2FMB478.8Unverified
#ModelMetricClaimedVerifiedStatus
1OFA-XHuman Explanation Rating85.7Unverified
2OFA-X-MTHuman Explanation Rating80.4Unverified
#ModelMetricClaimedVerifiedStatus
1OFA-X-MTHuman Explanation Rating77.3Unverified
2OFA-XHuman Explanation Rating68.9Unverified
#ModelMetricClaimedVerifiedStatus
1OFA-XHuman Explanation Rating89.5Unverified
2OFA-X-MTHuman Explanation Rating87.8Unverified