SimCSE achieves 76.3% unsupervised and 81.6% supervised Spearman's correlation on STS tasks with BERT-base, improving prior best results by 4.2% and 2.2% via simple contrastive learning.
hub
S em E val-2017 task 1: Semantic textual similarity multilingual and crosslingual focused evaluation
25 Pith papers cite this work, alongside 568 external citations. Polarity classification is still indexing.
25
Pith papers citing it
568
external citations · OpenAlex
hub tools
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
ALEE generates AMR-based English minimal pairs with fine-grained semantic shifts, translates them, and evaluates embedding models on 275+ languages to expose cross-lingual gaps linked to training data and tokenization.
Introduces P-CHR AUC and CRR metrics to demonstrate that semantic caching model selection is limited by calibration quality rather than ranking performance.
HTEB introduces dynamic, multi-axis evaluation of text embedding robustness using LLM transformations, finding decoupled profiles across models and that scaling does not close all robustness gaps.
LLMs exhibit positional bias and context-dependent scoring patterns when judging document similarity, with each model showing a stable scoring fingerprint but a shared hierarchy of sensitivity to different semantic perturbations.
PRIMETIME generator reveals that LLM datetime parsing and arithmetic primitives are individually unreliable but fully learnable via fine-tuning, enabling frontier-level accuracy on event planning with small LoRA models.
VLM2Vec converts state-of-the-art vision-language models into universal multimodal embedders via contrastive training on the new MMEB benchmark, delivering 10-20% absolute gains over prior models on both in-distribution and out-of-distribution tasks.
Task prompt vectors, formed by subtracting random initialization from tuned soft prompts, support low-resource initialization and arithmetic combination across tasks on 12 NLU datasets while remaining independent of initialization seed on two model architectures.
Adapting large language models by training only a low-rank decomposition BA added to frozen weight matrices matches full fine-tuning while cutting trainable parameters by orders of magnitude and adding no inference latency.
Schützen is a German-Bulgarian LLM safety dataset showing pronounced cross-language differences in model safety behavior.
Summing outputs from separately trained QLoRA PEFT modules provides strong performance for attribute-controlled text generation, often matching or exceeding single-task modules even on single-attribute tests.
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
Machine translation preserves embedding similarity structure for ten languages but distorts it for four in the Manifesto Corpus, via a new non-inferiority testing framework.
PEFT-Bench is a standardized end-to-end benchmark for 7 PEFT methods across 27 NLP datasets on autoregressive LLMs, accompanied by the PSCP metric that penalizes based on trainable parameters, inference speed, and training memory.
HyperAdapt performs parameter-efficient fine-tuning by row- and column-wise diagonal scaling to induce high-rank updates with only n+m trainable parameters.
SyMerge merges models via single-layer adaptation and expert-guided self-labeling to achieve task synergy, reporting SOTA results on vision, dense prediction, and NLP tasks.
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.
SuperGLUE is a new benchmark with more difficult language understanding tasks, a toolkit, and leaderboard to drive further progress beyond GLUE.
Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.
PromptRad reformulates multi-label radiology report classification as masked language modeling and enriches verbalizers with UMLS synonyms, outperforming baselines with only 32 training examples.
Re-evaluating controlled text generation systems under standardized conditions reveals that many published performance claims do not hold, highlighting the need for consistent evaluation practices.
Augmenting commonsense knowledge corpora with negation produces over 2M new triples that benefit LLM negation understanding when used for pre-training.
PEFT-Factory supplies a ready-to-use, extensible codebase that unifies 19 PEFT methods and evaluation pipelines for fine-tuning large autoregressive language models.
citing papers explorer
-
SimCSE: Simple Contrastive Learning of Sentence Embeddings
SimCSE achieves 76.3% unsupervised and 81.6% supervised Spearman's correlation on STS tasks with BERT-base, improving prior best results by 4.2% and 2.2% via simple contrastive learning.
-
ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs
ALEE generates AMR-based English minimal pairs with fine-grained semantic shifts, translates them, and evaluates embedding models on 275+ languages to expose cross-lingual gaps linked to training data and tokenization.
-
Closing the Calibration Gap in Semantic Caching
Introduces P-CHR AUC and CRR metrics to demonstrate that semantic caching model selection is limited by calibration quality rather than ranking performance.
-
The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness
HTEB introduces dynamic, multi-axis evaluation of text embedding robustness using LLM transformations, finding decoupled profiles across models and that scaling does not close all robustness gaps.
-
Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring
LLMs exhibit positional bias and context-dependent scoring patterns when judging document similarity, with each model showing a stable scoring fingerprint but a shared hierarchy of sensitivity to different semantic perturbations.
-
PRIMETIME : Limits of LLMs in Temporal Primitives
PRIMETIME generator reveals that LLM datetime parsing and arithmetic primitives are individually unreliable but fully learnable via fine-tuning, enabling frontier-level accuracy on event planning with small LoRA models.
-
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
VLM2Vec converts state-of-the-art vision-language models into universal multimodal embedders via contrastive training on the new MMEB benchmark, delivering 10-20% absolute gains over prior models on both in-distribution and out-of-distribution tasks.
-
Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
Task prompt vectors, formed by subtracting random initialization from tuned soft prompts, support low-resource initialization and arithmetic combination across tasks on 12 NLU datasets while remaining independent of initialization seed on two model architectures.
-
LoRA: Low-Rank Adaptation of Large Language Models
Adapting large language models by training only a low-rank decomposition BA added to frozen weight matrices matches full fine-tuning while cutting trainable parameters by orders of magnitude and adding no inference latency.
-
Sch\"utzen: Evaluating LLM Safety in Bulgarian and German Contexts
Schützen is a German-Bulgarian LLM safety dataset showing pronounced cross-language differences in model safety behavior.
-
Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation
Summing outputs from separately trained QLoRA PEFT modules provides strong performance for attribute-controlled text generation, often matching or exceeding single-task modules even on single-attribute tests.
-
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
-
Is Textual Similarity Invariant under Machine Translation? Evidence Based on the Political Manifesto Corpus
Machine translation preserves embedding similarity structure for ten languages but distorts it for four in the Manifesto Corpus, via a new non-inferiority testing framework.
-
PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark
PEFT-Bench is a standardized end-to-end benchmark for 7 PEFT methods across 27 NLP datasets on autoregressive LLMs, accompanied by the PSCP metric that penalizes based on trainable parameters, inference speed, and training memory.
-
HyperAdapt: Simple High-Rank Adaptation
HyperAdapt performs parameter-efficient fine-tuning by row- and column-wise diagonal scaling to induce high-rank updates with only n+m trainable parameters.
-
SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation
SyMerge merges models via single-layer adaptation and expert-guided self-labeling to achieve task synergy, reporting SOTA results on vision, dense prediction, and NLP tasks.
-
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
-
Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.
-
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
SuperGLUE is a new benchmark with more difficult language understanding tasks, a toolkit, and leaderboard to drive further progress beyond GLUE.
-
Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt
Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.
-
PromptRad: Knowledge-Enhanced Multi-Label Prompt-Tuning for Low-Resource Radiology Report Labeling
PromptRad reformulates multi-label radiology report classification as masked language modeling and enriches verbalizers with UMLS synonyms, outperforming baselines with only 32 training examples.
-
A Comparative Study of Controlled Text Generation Systems Using Level-Playing-Field Evaluation Principles
Re-evaluating controlled text generation systems under standardized conditions reveals that many published performance claims do not hold, highlighting the need for consistent evaluation practices.
-
Commonsense Knowledge with Negation: A Resource to Enhance Negation Understanding
Augmenting commonsense knowledge corpora with negation produces over 2M new triples that benefit LLM negation understanding when used for pre-training.
-
PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models
PEFT-Factory supplies a ready-to-use, extensible codebase that unifies 19 PEFT methods and evaluation pipelines for fine-tuning large autoregressive language models.
-
Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning
Data-CUBE applies a two-level curriculum (TSP-based task ordering via simulated annealing plus difficulty-sorted mini-batches) to multi-task instruction tuning and reports gains on MTEB sentence representation tasks.