SOTAVerified

nlg evaluation

Evaluate the generated text by NLG (Natural Language Generation) systems, like large language models

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 71 papers

TitleStatusHype
NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference ChecklistCode3
Towards a Unified Multi-Dimensional Evaluator for Text GenerationCode2
Is ChatGPT a Good NLG Evaluator? A Preliminary StudyCode1
G-Eval: NLG Evaluation using GPT-4 with Better Human AlignmentCode1
Leveraging Large Language Models for NLG Evaluation: Advances and ChallengesCode1
Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error SynthesisCode1
LUNA: A Framework for Language Understanding and Naturalness AssessmentCode1
Active Evaluation: Efficient NLG Evaluation with Few Pairwise ComparisonsCode1
Themis: A Reference-free NLG Evaluation Language Model with Flexibility and InterpretabilityCode1
Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement TheoryCode1
Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language GenerationCode1
Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying ReferencesCode0
Near-Negative Distinction: Giving a Second Life to Human Evaluation DatasetsCode0
Better than Random: Reliable NLG Human Evaluation with Constrained Active SamplingCode0
Long-Form Information Alignment Evaluation Beyond Atomic FactsCode0
One Prompt To Rule Them All: LLMs for Opinion Summary EvaluationCode0
A Study of Automatic Metrics for the Evaluation of Natural Language ExplanationsCode0
Describe me an Aucklet: Generating Grounded Perceptual Category DescriptionsCode0
CLSE: Corpus of Linguistically Significant EntitiesCode0
EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation MetricsCode0
DEBATE: Devil's Advocate-Based Assessment and Text EvaluationCode0
DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question AnsweringCode0
Are LLM-based Evaluators Confusing NLG Quality Criteria?Code0
Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and UnderstandingCode0
Analyzing and Evaluating Correlation Measures in NLG Meta-EvaluationCode0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.