Search Results for author:
Found 7 papers, 3 papers with code
Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes
The advent of Generative Artificial Intelligence (GenAI) models, including GitHub Copilot, OpenAI GPT, and Stable Diffusion, has revolutionized content creation, enabling non-professionals to produce high-quality content across various domains.
OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks
Evasion Attacks (EA) are used to test the robustness of trained neural networks by distorting input data to misguide the model into incorrect classifications.
Understanding Transformer Memorization Recall Through Idioms
In this work, we offer the first methodological framework for probing and characterizing recall of memorized sequences in transformer LMs.
Transformer Language Models without Positional Encodings Still Learn Positional Information
Causal transformer language models (LMs), such as GPT-3, typically require some form of positional encoding, such as positional embeddings.
SCROLLS: Standardized CompaRison Over Long Language Sequences
NLP benchmarks have largely focused on short texts, such as sentences and paragraphs, even though long texts comprise a considerable amount of natural language in the wild.
Ranked #8 on
Long-range modeling
on SCROLLS
Can Latent Alignments Improve Autoregressive Machine Translation?
Latent alignment objectives such as CTC and AXE significantly improve non-autoregressive machine translation models.
BERTese: Learning to Speak to BERT
In this work, we propose a method for automatically rewriting queries into "BERTese", a paraphrase query that is directly optimized towards better knowledge extraction.
