view post Post Reply Defending LLMs against Jailbreaking Attacks via Backtranslation (2402.16459)**Defending LLMs against Jailbreaking Attacks via Backtranslation**I really love this! Its a really innovative way to get robust defense against jailbreaking. Its not cheap, 2-3 calls per user request. But for some use-cases it can be worth it!
Cool Paper Names Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model Paper • 2310.17653 • Published Oct 26, 2023 • 2 Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch Paper • 2311.03099 • Published Nov 6, 2023 • 27 "I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming Paper • 2312.06908 • Published Dec 12, 2023 • 5 SaulLM-7B: A pioneering Large Language Model for Law Paper • 2403.03883 • Published Mar 6 • 68
Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model Paper • 2310.17653 • Published Oct 26, 2023 • 2
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch Paper • 2311.03099 • Published Nov 6, 2023 • 27
"I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming Paper • 2312.06908 • Published Dec 12, 2023 • 5
Datasets with Context abhi28577/nennepedia Viewer • Updated Jun 24, 2023 alinet/spoken_squad Viewer • Updated Jan 23 • 2 lucasmccabe/logiqa Viewer • Updated Feb 8, 2023 • 821 • 7 LLukas22/lfqa_preprocessed Viewer • Updated Jan 10, 2023 • 3
derek-thomas/Hubert_emotion-finetuned-gtzan-efficient Audio Classification • Updated Dec 24, 2023 • 14 • 1
derek-thomas/hubert-base-ls960-finetuned-gtzan-efficient-label-smoothed Audio Classification • Updated Aug 28, 2023 • 12