RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.
arXiv preprint arXiv:2305.14450 , pages=
4 Pith papers cite this work. Polarity classification is still indexing.
years
2026 4verdicts
UNVERDICTED 4representative citing papers
DiffuSent unifies ABSA subtasks via diffusion-based boundary denoising with contrastive training, reporting +2.48 F1 gains on multi-word triplets and up to 181x faster inference across 28 settings.
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.
Oxygen AIIC is an industrial platform using LLMs and VLMs for scalable item knowledge production and service at JD.com, reporting 94.2% precision and 82.8% recall along with business metric improvements.
citing papers explorer
-
Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling
RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.
-
DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis
DiffuSent unifies ABSA subtasks via diffusion-based boundary denoising with contrastive training, reporting +2.48 F1 gains on multi-word triplets and up to 181x faster inference across 28 settings.
-
Task Decomposition for Efficient Annotation
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.
-
JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications
Oxygen AIIC is an industrial platform using LLMs and VLMs for scalable item knowledge production and service at JD.com, reporting 94.2% precision and 82.8% recall along with business metric improvements.