On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “prefix-tuning”

On Robust Prefix-Tuning for Text Classificationcs.CL

A new robust prefix-tuning framework improves model robustness against adversarial attacks.

problem Lack of robustness in prefix-tuning for adversarial attacks.

method Leveraging layerwise activations of pretrained models for additional prefix finetuning during the test phase.

result Framework substantially improves robustness over strong baselines while maintaining comparable accuracy on clean texts.

prefix-tuning adversarial attacks robustness text classification modularity

2022-03-19abs ↗pdf ↗

Discourse-Aware Soft Prompting for Text Generationcs.CL

Improved text generation with discourse-aware soft prompts.

problem Efficient fine-tuning methods don't generalize across all generation tasks.

method Hierarchical blocking and attention sparsity on prefix parameters.

result Structured design of prefix parameters yields more coherent generations.

text generation soft prompts discourse structure prefix-tuning attention sparsity

2021-12-10abs ↗pdf ↗

Learning Better Intent Representations for Financial Open Intent Classificationcs.CL

Improved financial VA intent classification accuracy.

problem Determining user intents for unseen open intents.

method Supervised pre-training of intent representations using prefix-tuning and fine-tuning.

result 1.63% - 2.07% higher accuracy on banking77 benchmark.

financial VA intent classification open intents prefix-tuning fine-tuning

2022-10-25abs ↗pdf ↗

Understanding Prompt Tuning and In-Context Learning via Meta-Learningcs.LG

This paper explains how to optimize prompts for model adaptation.

problem Understanding and optimizing prompt tuning for model adaptation.

method Bayesian view and meta-learning to explain prompt optimization.

result Optimal prompting can be studied formally as conditioning Bayesian predictors.

prompt tuning in-context learning meta-learning Bayesian predictors weight tuning

2025-05-22abs ↗pdf ↗

Elicitation without Backpropagation: Steering Model Behavior by Optimizing the Latent Posteriorcs.LG

PPT optimizes transformer behavior by steering its latent posterior using prior samples.

problem Eliciting desired behavior from transformers without backpropagation.

method Posterior Prefix Tuning (PPT) uses predictive Monte Carlo (PMC) samples and importance sampling to optimize the latent posterior.

result PPT optimizes transformer behavior without backpropagation, achieving high utility across different utility functions.

Transformer Behavior Latent Posterior Posterior Prefix Tuning Predictive Monte Carlo Importance Sampling

2026-07-21abs ↗pdf ↗