Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues

Q Ren, H Li, D Liu, Z **e, X Lu, Y Qiao, L Sha… - arxiv preprint arxiv …, 2024 - arxiv.org
This study exposes the safety vulnerabilities of Large Language Models (LLMs) in multi-turn
interactions, where malicious users can obscure harmful intents across several queries. We …

[PDF][PDF] Investigating asr error correction with large language model and multilingual 1-best hypotheses

S Li, C Chen, CY Kwok, C Chu, ES Chng… - Proc. Interspeech, 2024 - isca-archive.org
This paper investigates using pre-trained large language models (LLMs) to improve
multilingual automatic speech recognition (ASR) outputs. Current popular methods involve …

Preference tuning with human feedback on language, speech, and vision tasks: A survey

GI Winata, H Zhao, A Das, W Tang, DD Yao… - arxiv preprint arxiv …, 2024 - arxiv.org
Preference tuning is a crucial process for aligning deep generative models with human
preferences. This survey offers a thorough overview of recent advancements in preference …