activity
20232025
most citedBaseline Defenses for Adversarial Attacks Against Aligned Language Models

37 citations · 52 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2025

Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs

Ryan Synk, Monte Hoover, John Kirchenbauer +6

There is growing demand for performing inference with hundreds of thousands of input tokens on trained transformer models. Inference at this extreme scale demands significant compu…

cs.CL2024

GenQA: Generating Millions of Instructions from a Handful of Prompts

Jiuhai Chen, Rifaa Qadri, Yuxin Wen +4

Most public instruction finetuning datasets are relatively small compared to the closed source datasets used to train industry models. To study questions about finetuning at scale,…

cs.CL2024

LiveBench: A Challenging, Contamination-Limited LLM Benchmark

Colin White, Samuel Dooley, Manley Roberts +15

Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render ben…

cs.CL2024

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

Abhimanyu Hans, Yuxin Wen, Neel Jain +8

Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle modification to the next-tok…

cs.CL202314 cited

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Neel Jain, Ping-yeh Chiang, Yuxin Wen +10

We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation. NEFTune adds noise to the embedding vectors during training. Standard fi…

cs.CL2023

Bring Your Own Data! Self-Supervised Evaluation for Large Language Models

Neel Jain, Khalid Saifullah, Yuxin Wen +6

With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative. For example, a…