ComPaSS estimates commonsense plausibility by quantifying semantic shifts induced by augmenting sentences with related information and outperforms generative baselines on fine-grained tasks for language and vision-language models.
IEEE/ACM Transactions on Audio, Speech, and Lan- guage Processing, 30:594–604
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
DocRetriever introduces a framework using layout-aware sparse embeddings for hybrid encoding without OCR and a generalizable reasoning-augmented reranker for few-shot settings, plus the MultiDocR benchmark for evaluation.
AGREE boosts visual document retrieval by adding local relevance signals from MLLM attention maps to global document labels during retriever training.
citing papers explorer
-
Estimating Commonsense Plausibility through Semantic Shifts
ComPaSS estimates commonsense plausibility by quantifying semantic shifts induced by augmenting sentences with related information and outperforms generative baselines on fine-grained tasks for language and vision-language models.
-
DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark
DocRetriever introduces a framework using layout-aware sparse embeddings for hybrid encoding without OCR and a generalizable reasoning-augmented reranker for few-shot settings, plus the MultiDocR benchmark for evaluation.
-
Attention Grounded Enhancement for Visual Document Retrieval
AGREE boosts visual document retrieval by adding local relevance signals from MLLM attention maps to global document labels during retriever training.