ContinuousBench shows non-private synthetic text transfers corpus-specific capabilities while state-of-the-art DP methods fail to do so even at ε=100.
Character-level Convolutional Networks for Text Classification
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.
representative citing papers
Uniform diffusion models rely on a leave-one-out denoiser rather than the usual denoising posterior, with exact conversions derived; an absorbing-state reformulation is introduced that matches or exceeds masked diffusion on language modeling while preserving the original joint distribution.
Vacuity-based OOD detection in evidential deep learning is highly sensitive to class cardinality differences between ID and OOD, which can artificially inflate AUROC and AUPR without any change in model predictions.
Meta-Harness discovers improved harness code for LLMs via agentic search over prior execution traces, yielding 7.7-point gains on text classification with 4x fewer tokens and 4.7-point gains on math reasoning across held-out models.
Scaling and instruction tuning increase sycophancy in LLMs on opinion and fact tasks, but a synthetic data fine-tuning intervention reduces it on held-out prompts.
Coupled constraints on weight updates in a safety subspace and regularization of SAE-identified safety features preserve LLM refusal behaviors during fine-tuning better than weight-only or activation-only methods.
An unsupervised character-level CNN encoder with attention-based RNN decoder, trained on Clueweb09 anchor phrases, generates query reformulations that improve retrieval on TREC collections.
GradShield is a data filtering technique using FIHS scores and adaptive thresholding to prevent safety misalignment in finetuned LLMs while preserving utility.
Empirical tests on three LLMs show prompt semantics and task keywords drive inference energy costs more than length, with varying patterns by task.
Compares BERT, ESP, and Cui2Vec embeddings within ESIM on the MedNLI shared-task dataset to assess performance and internal representations for medical inference.
citing papers explorer
-
ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
ContinuousBench shows non-private synthetic text transfers corpus-specific capabilities while state-of-the-art DP methods fail to do so even at ε=100.
-
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
Uniform diffusion models rely on a leave-one-out denoiser rather than the usual denoising posterior, with exact conversions derived; an absorbing-state reformulation is introduced that matches or exceeds masked diffusion on language modeling while preserving the original joint distribution.
-
Rethinking Vacuity for OOD Detection in Evidential Deep Learning
Vacuity-based OOD detection in evidential deep learning is highly sensitive to class cardinality differences between ID and OOD, which can artificially inflate AUROC and AUPR without any change in model predictions.
-
Meta-Harness: End-to-End Optimization of Model Harnesses
Meta-Harness discovers improved harness code for LLMs via agentic search over prior execution traces, yielding 7.7-point gains on text classification with 4x fewer tokens and 4.7-point gains on math reasoning across held-out models.
-
Simple synthetic data reduces sycophancy in large language models
Scaling and instruction tuning increase sycophancy in LLMs on opinion and fact tasks, but a synthetic data fine-tuning intervention reduces it on held-out prompts.
-
Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints
Coupled constraints on weight updates in a safety subspace and regularization of SAE-identified safety features preserve LLM refusal behaviors during fine-tuning better than weight-only or activation-only methods.
-
Learning to Reformulate the Queries on the WEB
An unsupervised character-level CNN encoder with attention-based RNN decoder, trained on Clueweb09 anchor phrases, generates query reformulations that improve retrieval on TREC collections.
-
GradShield: Alignment Preserving Finetuning
GradShield is a data filtering technique using FIHS scores and adaptive thresholding to prevent safety misalignment in finetuned LLMs while preserving utility.
-
Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference
Empirical tests on three LLMs show prompt semantics and task keywords drive inference energy costs more than length, with varying patterns by task.
-
UW-BHI at MEDIQA 2019: An Analysis of Representation Methods for Medical Natural Language Inference
Compares BERT, ESP, and Cui2Vec embeddings within ESIM on the MedNLI shared-task dataset to assess performance and internal representations for medical inference.