Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Can AI Really Fix Your Code? Putting Code-Editing LLMs to the Test

Beck LaBash|August Rosedale|Alex Reents|Lucas Negritto|Colin Wiel

Ragnarok: A New Dawn for Retrieval-Augmented Generation

Ronak Pradeep|Nandan Thakur|Sahel Sharifymoghaddam|Eric Zhang|Ryan Nguyen|Daniel Campos|Nick Craswell|Jimmy Lin

Unlocking LLMs: Decoding the Secrets of Better Text Generation

Sean Welleck|Amanda Bertsch|Matthew Finlayson|Hailey Schoelkopf|Alex Xie|Graham Neubig|Ilia Kulikov|Zaid Harchaoui

Can AI Really See Charts? Testing Visualization Literacy in Multimodal LLMs

Zhimin Li|Haichao Miao|Valerio Pascucci|Shusen Liu

EAGLE-2 Takes Flight: Making LLMs Faster Than Ever

Yuhui Li|Fangyun Wei|Chao Zhang|Hongyang Zhang

Are LLMs More Rational Than Humans?

Ryan Liu|Jiayi Geng|Joshua C. Peterson|Ilia Sucholutsky|Thomas L. Griffiths

Exposing and Removing Backdoors in AI: Protecting LLMs From Hidden Threats

Yi Zeng|Weiyu Sun|Tran Ngoc Huynh|Dawn Song|Bo Li|Ruoxi Jia

Unlocking AI’s Hidden Knowledge: Guiding Attention in Large Language Models

Meiru Zhang|Zaiqiao Meng|Nigel Collier

Can AI Find New Ways to Break Itself? Unmasking Hidden Vulnerabilities in Safety Classifiers

Yash Kumar Lal|Preethi Lahoti|Aradhana Sinha|Yao Qin|Ananth Balashankar

The first platform built for prompt engineering