TabEmbed is the first generalist embedding model for tabular data that unifies classification and retrieval in one space via contrastive learning and outperforms text embedding models on the new TabBench benchmark.
hub
Simcse: Simple contrastive learning of sentence embeddings
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Semantic Recall is a new evaluation metric for approximate nearest neighbor search that focuses only on semantically relevant results, with Tolerant Recall as a proxy when relevance labels are unavailable.
mEOL creates aligned embeddings for text, images, and SVGs using instruction-guided MLLM one-word summaries and semantic SVG rewriting, outperforming baselines on a new text-to-SVG retrieval benchmark.
M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.
MIPIC trains nested Matryoshka representations via self-distilled intra-relational alignment with top-k CKA and progressive information chaining across depths, yielding competitive performance especially at extreme low dimensions.
RePrompT uses recurrent prompt tuning to inject prior-visit latent states and cohort-derived population prompt tokens into LLMs, yielding better performance than pure EHR or pure LLM baselines on MIMIC clinical prediction tasks.
UniCon unifies contrastive alignment across encoders and alignment types using kernels to enable exact closed-form updates instead of stochastic optimization.
Parameter-efficient fine-tuning lets MLLMs serve as effective retrievers for natural-language-guided cross-view geo-localization, beating dual-encoder baselines on GeoText-1652 and CVG-Text while using far fewer trainable parameters.
Bias toward LLM texts in neural retrievers arises from artifact imbalances between positive and negative documents in training data that are absorbed during contrastive learning.
A governed LLM routing system for lab tutoring raises challenge-alignment from 0.90 to 0.98, boosts productive-struggle time, and cuts token costs by two-thirds while preserving answer accuracy.
Contrastive learning trains unsupervised dense retrievers that beat BM25 on most BEIR datasets and support cross-lingual retrieval across scripts.
SimReg regularization accelerates LLM pretraining convergence by over 30% and raises average zero-shot performance by over 1% across benchmarks.
ACSE estimates LLM prompt uncertainty via adaptive clustering of semantic entropy across multiple responses and uses conformal prediction to bound error rates on accepted answers with distribution-free guarantees.
G-Loss builds a document-similarity graph and uses semi-supervised label propagation to guide fine-tuning of language models, yielding higher accuracy than standard losses on five classification benchmarks.
A new pre-training task that maps languages bidirectionally in embedding space improves machine translation by up to 11.9 BLEU, cross-lingual QA by 6.72 BERTScore points, and understanding accuracy by over 5% over strong baselines.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
Fine-tuned LLaMA3 with LoRA reaches 81.24% F1 on 18-category fine-grained medical entity recognition, beating zero-shot by 63.11% and few-shot by 35.63%.
citing papers explorer
-
Beyond the Basics: Leveraging Large Language Model for Fine-Grained Medical Entity Recognition
Fine-tuned LLaMA3 with LoRA reaches 81.24% F1 on 18-category fine-grained medical entity recognition, beating zero-shot by 63.11% and few-shot by 35.63%.