SOTAVerified

Informativeness

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 451–500 of 735 papers

TitleStatusHype
CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization—0
QBox: Partial Transfer Learning with Active Querying for Object DetectionCode0
Reputation dependent pricing strategy: analysis based on a Chinese C2C marketplace—0
LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates—0
Bayesian Active Learning for Sim-to-Real Robotic Perception—0
Investigating Entropy for Extractive Document Summarization—0
Overinference from Weak Signals and Underinference from Strong Signals—0
Naturalness Evaluation of Natural Language Generation in Task-oriented Dialogues using BERT—0
On Reducing Repetition in Abstractive Summarization—0
Ranking Online Reviews Based on Their Helpfulness: An Unsupervised Approach—0
Predicting Informativeness of Semantic Triples—0
Deep Active Learning for Text Classification with Diverse Interpretations—0
The Many Dimensions of Truthfulness: Crowdsourcing Misinformation Assessments on a Multidimensional ScaleCode0
Active Curriculum Learning—0
Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning—0
SumPubMed: Summarization Dataset of PubMed Scientific ArticlesCode1
Predicting pragmatic discourse features in the language of adults with autism spectrum disorder—0
When Deep Learners Change Their Mind: Learning Dynamics for Active Learning—0
Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features—0
Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered BeneficialCode0
Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes—0
Orthonormal Product Quantization Network for Scalable Face Image RetrievalCode0
Deep Learning Image Recognition for Non-images—0
MEAL: Manifold Embedding-based Active Learning—0
BARTScore: Evaluating Generated Text as Text GenerationCode1
Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders—0
Semantic-Enhanced Explainable Finetuning for Open-Domain Dialogues—0
Generating Informative Conclusions for Argumentative TextsCode0
Coherent and Concise Radiology Report Generation via Context Specific Image Representations and Orthogonal Sentence States—0
Near-Optimal Multi-Perturbation Experimental Design for Causal Structure LearningCode0
THINK: A Novel Conversation Model for Generating Grammatically Correct and Coherent Responses—0
Rethinking InfoNCE: How Many Negative Samples Do You Need?—0
Cost-Accuracy Aware Adaptive Labeling for Active LearningCode0
LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active LearningCode1
Imagine, Reason and Write: Visual Storytelling with Graph Knowledge and Relational Reasoning—0
Towards Human-Free Automatic Quality Evaluation of German Summarization—0
Knowledge-based Review Generation by Coherence Enhanced Text Planning—0
Towards Clinical Encounter Summarization: Learning to Compose Discharge Summaries from Prior Notes—0
Meta-evaluation of Conversational Search Evaluation MetricsCode0
Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentation—0
Low-Regret Active learning—0
Uncertainty-Aware Annotation Protocol to Evaluate Deformable Registration AlgorithmsCode0
Generating Weather Comments from Meteorological SimulationsCode0
Active Learning for Deep Object Detection via Probabilistic ModelingCode1
Multimodal assessment of apparent personality using feature attention and error consistency constraint—0
Combining Reward Information from Multiple Sources—0
Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach—0
Towards the evaluation of automatic simultaneous speech translation from a communicative perspective—0
Advisors with Hidden Motives—0
Linear Regression over Networks with Communication Guarantees—0
Show:102550
← PrevPage 10 of 15Next →

No leaderboard results yet.