Post-hoc truncation of the tail of the SVD of ΔW reduces spurious-group gaps by up to 5× with <2 pp accuracy loss across 0.5B–7B models and four benchmarks.
Natural Language Understanding with the Quora Question Pairs Dataset
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
This paper explores the task Natural Language Understanding (NLU) by looking at duplicate question detection in the Quora dataset. We conducted extensive exploration of the dataset and used various machine learning models, including linear and tree-based models. Our final finding was that a simple Continuous Bag of Words neural network model had the best performance, outdoing more complicated recurrent and attention based models. We also conducted error analysis and found some subjectivity in the labeling of the dataset.
citation-role summary
dataset 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
dataset 1polarities
use dataset 1representative citing papers
BiCo transfers task vectors across models differing in width, depth, and pre-training by estimating dual-space orthogonal Procrustes mappings from one forward-backward pass on a calibration set.
FedPower improves the accuracy-privacy tradeoff in differentially private LoRA-based federated learning by reconstructing and clipping full-rank updates then using PowerDP to inject noise before orthonormalization in low-rank factorization.
H-TokCom groups tokens by semantic similarity and protects cluster-level bits with higher power, raising semantic similarity from 0.206 to 0.279 at 3 dB SNR on COCO data.
A convex KMM-based valuation method that accounts for both target-task alignment and inter-dataset redundancy in gradient space outperforms standard gradient-alignment baselines for LLM post-training data selection.
ML-Embed releases open multilingual embedding models trained with a new 3D-ML framework that reportedly set new MTEB records on 9 of 17 benchmarks, especially in low-resource languages.
citing papers explorer
-
Improving Parameter-Efficient Federated Learning with Differentially Private Refactorization
FedPower improves the accuracy-privacy tradeoff in differentially private LoRA-based federated learning by reconstructing and clipping full-rank updates then using PowerDP to inject noise before orthonormalization in low-rank factorization.