SOTAVerified

Semantic Textual Similarity

Semantic textual similarity deals with determining how similar two pieces of texts are. This can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.

Image source: Learning Semantic Textual Similarity from Conversations

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 2381 papers

TitleStatusHype
HSI: A Holistic Style Injector for Arbitrary Style Transfer—0
Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution—0
Transformer Semantic Genetic Programming for Symbolic Regression—0
Fake News Detection After LLM Laundering: Measurement and ExplanationCode0
Feedback-Aware Monte Carlo Tree Search for Efficient Information Seeking in Goal-Oriented Conversations—0
Recommending Actionable Strategies: A Semantic Approach to Integrating Analytical Frameworks with Decision Heuristics—0
Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMsCode0
A Comprehensive Framework for Semantic Similarity Analysis of Human and AI-Generated Text Using Transformer Architectures and Ensemble Techniques—0
Rethinking the Sample Relations for Few-Shot ClassificationCode7
2-Tier SimCSE: Elevating BERT for Robust Sentence Embeddings—0
Sequence Spreading-Based Semantic Communication Under High RF Interference—0
LegalGuardian: A Privacy-Preserving Framework for Secure Integration of Large Language Models in Legal Practice—0
MedFILIP: Medical Fine-grained Language-Image Pre-trainingCode1
Evaluating GenAI for Simplifying Texts for Education: Improving Accuracy and Consistency for Enhanced Readability—0
Consistency of Responses and Continuations Generated by Large Language Models on Social Media—0
Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI—0
GeAR: Generation Augmented Retrieval—0
Universal Features Guided Zero-Shot Category-Level Object Pose Estimation—0
Harnessing Frozen Unimodal Encoders for Flexible Multimodal AlignmentCode0
Anchor-Aware Similarity Cohesion in Target Frames Enables Predicting Temporal Moment Boundaries in 2DCode0
ProtCLIP: Function-Informed Protein Multi-Modal Learning—0
Multiple References with Meaningful Variations Improve Literary Machine Translation—0
Reasoning to Attend: Try to Understand How <SEG> Token WorksCode2
DiffSim: Taming Diffusion Models for Evaluating Visual SimilarityCode1
HashAttention: Semantic Sparsity for Faster Inference—0
DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image SegmentationCode1
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs—0
Quantifying Positional Biases in Text Embedding ModelsCode0
Familiarity: Better Evaluation of Zero-Shot Named Entity Recognition by Quantifying Label Shifts in Synthetic Training DataCode1
Single-View Graph Contrastive Learning with Soft Neighborhood AwarenessCode0
jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images—0
Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource LanguagesCode0
Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT—0
SiReRAG: Indexing Similar and Related Information for Multihop Reasoning—0
Detecting Redundant Health Survey Questions Using Language-agnostic BERT Sentence Embedding (LaBSE)—0
Human Variability vs. Machine Consistency: A Linguistic Analysis of Texts Generated by Humans and Large Language Models—0
VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding—0
Interpretable Company Similarity with Sparse Autoencoders—0
TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual SimilarityCode0
Quantifying perturbation impacts for large language models—0
Vid-Morp: Video Moment Retrieval Pretraining from Unlabeled Videos in the WildCode1
Generative Semantic Communication for Joint Image Transmission and Segmentation—0
RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable DataCode1
Isolating authorship from content with semantic embeddings and contrastive learning—0
In-Context Experience Replay Facilitates Safety Red-Teaming of Text-to-Image Diffusion Models—0
BanglaEmbed: Efficient Sentence Embedding Models for a Low-Resource Language Using Cross-Lingual Distillation Techniques—0
FAST-Splat: Fast, Ambiguity-Free Semantics Transfer in Gaussian Splatting—0
HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives—0
Advancing Large Language Models for Spatiotemporal and Semantic Association Mining of Similar Environmental Events—0
Membership Inference Attack against Long-Context Large Language Models—0
Show:102550
← PrevPage 4 of 48Next →
All datasetsSTS BenchmarkMTEBMRPCSICKSTS13STS14STS12STS15STS16MRPC DevSentEvalSICK-R

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SMARTRoBERTaDev Pearson Correlation92.8—Unverified
2DeBERTa (large)Accuracy92.5—Unverified
3SMART-BERTDev Pearson Correlation90—Unverified
4MT-DNN-SMARTPearson Correlation0.93—Unverified
5StructBERTRoBERTa ensemblePearson Correlation0.93—Unverified
6Mnet-SimPearson Correlation0.93—Unverified
7XLNet (single model)Pearson Correlation0.93—Unverified
8T5-11BPearson Correlation0.93—Unverified
9ALBERTPearson Correlation0.93—Unverified
10RoBERTaPearson Correlation0.92—Unverified
#ModelMetricClaimedVerifiedStatus
1AnglE-UAESpearman Correlation84.54—Unverified
2ST5-XXLSpearman Correlation82.63—Unverified
3ST5-LargeSpearman Correlation81.83—Unverified
4ST5-XLSpearman Correlation81.66—Unverified
5ST5-BaseSpearman Correlation81.14—Unverified
6MPNet-multilingualSpearman Correlation80.73—Unverified
7SGPT-5.8B-nliSpearman Correlation80.53—Unverified
8MPNetSpearman Correlation80.28—Unverified
9MiniLM-L12Spearman Correlation79.8—Unverified
10SimCSE-BERT-supSpearman Correlation79.12—Unverified
#ModelMetricClaimedVerifiedStatus
1MT-DNN-SMARTAccuracy93.7—Unverified
2ALBERTAccuracy93.4—Unverified
3RoBERTa (ensemble)Accuracy92.3—Unverified
4BigBirdF191.5—Unverified
5StructBERTRoBERTa ensembleAccuracy91.5—Unverified
6FLOATER-largeAccuracy91.4—Unverified
7SMARTAccuracy91.3—Unverified
8RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned)Accuracy91—Unverified
9RoBERTa-large 355M + Entailment as Few-shot LearnerF191—Unverified
10SpanBERTAccuracy90.9—Unverified
#ModelMetricClaimedVerifiedStatus
1PromCSE-RoBERTa-large (0.355B)Spearman Correlation0.82—Unverified
2PromptEOL+CSE+LLaMA-30BSpearman Correlation0.82—Unverified
3PromptEOL+CSE+OPT-13BSpearman Correlation0.82—Unverified
4SimCSE-RoBERTalargeSpearman Correlation0.82—Unverified
5PromptEOL+CSE+OPT-2.7BSpearman Correlation0.81—Unverified
6SentenceBERTSpearman Correlation0.75—Unverified
7SRoBERTa-NLI-baseSpearman Correlation0.74—Unverified
8SRoBERTa-NLI-largeSpearman Correlation0.74—Unverified
9Dino (STS/̄🦕)Spearman Correlation0.74—Unverified
10SBERT-NLI-largeSpearman Correlation0.74—Unverified
#ModelMetricClaimedVerifiedStatus
1AnglE-LLaMA-7BSpearman Correlation0.91—Unverified
2AnglE-LLaMA-7B-v2Spearman Correlation0.91—Unverified
3PromptEOL+CSE+LLaMA-30BSpearman Correlation0.9—Unverified
4PromptEOL+CSE+OPT-13BSpearman Correlation0.9—Unverified
5PromptEOL+CSE+OPT-2.7BSpearman Correlation0.9—Unverified
6PromCSE-RoBERTa-large (0.355B)Spearman Correlation0.89—Unverified
7Trans-Encoder-BERT-large-bi (unsup.)Spearman Correlation0.89—Unverified
8Trans-Encoder-BERT-large-cross (unsup.)Spearman Correlation0.88—Unverified
9Trans-Encoder-RoBERTa-large-cross (unsup.)Spearman Correlation0.88—Unverified
10SimCSE-RoBERTa-largeSpearman Correlation0.87—Unverified