Search Results - "Kirchenbauer, John"

What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability by Kirchenbauer, John, Oaks, Jacob, Heim, Eric

“…Classifier calibration has received recent attention from the machine learning community due both to its practical utility in facilitating decision making, as…”
Get full text

Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust by Wen, Yuxin, Kirchenbauer, John, Geiping, Jonas, Goldstein, Tom

“…Watermarking the outputs of generative models is a crucial technique for tracing copyright and preventing potential harm from AI-generated content. In this…”
Get full text

GenQA: Generating Millions of Instructions from a Handful of Prompts by Chen, Jiuhai, Qadri, Rifaa, Wen, Yuxin, Jain, Neel, Kirchenbauer, John, Zhou, Tianyi, Goldstein, Tom

“…Most public instruction finetuning datasets are relatively small compared to the closed source datasets used to train industry models. To study questions about…”
Get full text

LMD3: Language Model Data Density Dependence by Kirchenbauer, John, Honke, Garrett, Somepalli, Gowthami, Geiping, Jonas, Ippolito, Daphne, Lee, Katherine, Goldstein, Tom, Andre, David

“…We develop a methodology for analyzing language model task performance at the individual example level based on training data density estimation. Experiments…”
Get full text

OPTune: Efficient Online Preference Tuning by Chen, Lichang, Chen, Jiuhai, Liu, Chenxi, Kirchenbauer, John, Soselia, Davit, Zhu, Chen, Goldstein, Tom, Zhou, Tianyi, Huang, Heng

“…Reinforcement learning with human feedback~(RLHF) is critical for aligning Large Language Models (LLMs) with human preference. Compared to the widely studied…”
Get full text

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery by Wen, Yuxin, Jain, Neel, Kirchenbauer, John, Goldblum, Micah, Geiping, Jonas, Goldstein, Tom

“…The strength of modern generative models lies in their ability to be controlled through text-based prompts. Typical "hard" prompts are made from interpretable…”
Get full text

A Watermark for Large Language Models by Kirchenbauer, John, Geiping, Jonas, Wen, Yuxin, Katz, Jonathan, Miers, Ian, Goldstein, Tom

“…Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to…”
Get full text

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs by Hans, Abhimanyu, Wen, Yuxin, Jain, Neel, Kirchenbauer, John, Kazemi, Hamid, Singhania, Prajwal, Singh, Siddharth, Somepalli, Gowthami, Geiping, Jonas, Bhatele, Abhinav, Goldstein, Tom

“…Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle…”
Get full text

Transformers Can Do Arithmetic with the Right Embeddings by McLeish, Sean, Bansal, Arpit, Stein, Alex, Jain, Neel, Kirchenbauer, John, Bartoldson, Brian R, Kailkhura, Bhavya, Bhatele, Abhinav, Geiping, Jonas, Schwarzschild, Avi, Goldstein, Tom

“…The poor performance of transformers on arithmetic tasks seems to stem in large part from their inability to keep track of the exact position of each digit…”
Get full text

Bring Your Own Data! Self-Supervised Evaluation for Large Language Models by Jain, Neel, Saifullah, Khalid, Wen, Yuxin, Kirchenbauer, John, Shu, Manli, Saha, Aniruddha, Goldblum, Micah, Geiping, Jonas, Goldstein, Tom

“…With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is…”
Get full text

On the Reliability of Watermarks for Large Language Models by Kirchenbauer, John, Geiping, Jonas, Wen, Yuxin, Shu, Manli, Saifullah, Khalid, Kong, Kezhi, Fernando, Kasun, Saha, Aniruddha, Goldblum, Micah, Goldstein, Tom

“…As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is…”
Get full text

Baseline Defenses for Adversarial Attacks Against Aligned Language Models by Jain, Neel, Schwarzschild, Avi, Wen, Yuxin, Somepalli, Gowthami, Kirchenbauer, John, Chiang, Ping-yeh, Goldblum, Micah, Saha, Aniruddha, Geiping, Jonas, Goldstein, Tom

“…As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers…”
Get full text

NEFTune: Noisy Embeddings Improve Instruction Finetuning by Jain, Neel, Chiang, Ping-yeh, Wen, Yuxin, Kirchenbauer, John, Chu, Hong-Min, Somepalli, Gowthami, Bartoldson, Brian R, Kailkhura, Bhavya, Schwarzschild, Avi, Saha, Aniruddha, Goldblum, Micah, Geiping, Jonas, Goldstein, Tom

“…We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation. NEFTune adds noise to the embedding vectors during…”
Get full text