Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Soft Begging: How to Protect LLMs from Prompt Injection

Simon Ostermann|Kevin Baum|Christoph Endres|Julia Masloh|Patrick Schramowski

Unlocking Self-Correction in Language Models

Haritz Puerto|Tilek Chubakov|Xiaodan Zhu|Harish Tayyar Madabushi|Iryna Gurevych

Unlocking Math's Secrets: How TheoremLlama Turns LLMs into Lean4 Experts

Ruida Wang|Jipeng Zhang|Yizhen Jia|Rui Pan|Shizhe Diao|Renjie Pi|Tong Zhang

The Unexpected Language Gap in Quantized AI

Kelly Marchisio|Saurabh Dash|Hongyu Chen|Dennis Aumiller|Ahmet Üstün|Sara Hooker|Sebastian Ruder

Unlocking the Power of LLMs for Event Sequences: ESQA Explained

Irina Abdullaeva|Andrei Filatov|Mikhail Orlov|Ivan Karpukhin|Viacheslav Vasilev|Denis Dimitrov|Andrey Kuznetsov|Ivan Kireev|Andrey Savchenko

This Single Character Can Break AI Chatbots

Leon Lin|Hannah Brown|Kenji Kawaguchi|Michael Shieh

Can LLMs Evaluate Their Own Safety? New Research Says Yes

Hannah Brown|Leon Lin|Kenji Kawaguchi|Michael Shieh

Can LLMs Predict Their Own Hallucinations?

Ziwei Ji|Delong Chen|Etsuko Ishii|Samuel Cahyawijaya|Yejin Bang|Bryan Wilie|Pascale Fung

Unlocking Infectious Disease Secrets with Synthetic Data

Styliani-Christina Fragkouli|Dhwani Solanki|Leyla J Castro|Fotis E Psomopoulos|Núria Queralt-Rosinach|Davide Cirillo|Lisa C Crossman

The first platform built for prompt engineering