A GenAI-based method extracts representations from unstructured data and uses a neural network to fit marginal structural models that recover causal effects of treatment feature sequences including their positions.
Scaling sentence embeddings with large language models.arXiv preprint arXiv:2307.16645
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
LLMs exhibit mid-layer representation advantage for recommendations; MARC compresses representations modularly to reduce costs while improving performance, as shown in a large-scale online advertising deployment.
A prompt-and-layer tweak lets pretrained multimodal LLMs serve as competitive retrieval systems without any additional training, with reranking framed as multiple-choice questions to reduce label bias.
E5-V produces strong universal multimodal embeddings from MLLMs trained solely on text pairs, often surpassing prior methods across retrieval and related tasks without multimodal fine-tuning.
ELVA uses rule-based RL rewards to rank negatives by similarity, reducing grain blindness in universal multimodal retrieval and reporting a 13.1% gain on a new multi-grain benchmark.
SSA-ME uses saliency-aware modeling to reduce visual neglect and semantic drift, achieving SOTA results on the MMEB benchmark for multimodal retrieval.
citing papers explorer
-
GenAI Powered Dynamic Causal Inference with Unstructured Data
A GenAI-based method extracts representations from unstructured data and uses a neural network to fit marginal structural models that recover causal effects of treatment feature sequences including their positions.
-
Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
LLMs exhibit mid-layer representation advantage for recommendations; MARC compresses representations modularly to reduce costs while improving performance, as shown in a large-scale online advertising deployment.
-
FreeRet: MLLMs as Training-Free Retrievers
A prompt-and-layer tweak lets pretrained multimodal LLMs serve as competitive retrieval systems without any additional training, with reranking framed as multiple-choice questions to reduce label bias.
-
E5-V: Universal Embeddings with Multimodal Large Language Models
E5-V produces strong universal multimodal embeddings from MLLMs trained solely on text pairs, often surpassing prior methods across retrieval and related tasks without multimodal fine-tuning.
-
ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval
ELVA uses rule-based RL rewards to rank negatives by similarity, reducing grain blindness in universal multimodal retrieval and reporting a 13.1% gain on a new multi-grain benchmark.
-
Combating Visual Neglect and Semantic Drift in Large Multimodal Models for Enhanced Cross-Modal Retrieval
SSA-ME uses saliency-aware modeling to reduce visual neglect and semantic drift, achieving SOTA results on the MMEB benchmark for multimodal retrieval.