Encoding and decoding😂

Genuinely curious: is it a good timing for academic NLP people to switch the gear a little bit and work on more interdisciplinary stuff? If so, what interdisciplinary direction "NLP+X" would you recommend?

A war over Taiwan could involve a new generation of arms, causing untold destruction and escalating unpredictably. This is how to avert it econ.st/3mVZLKs

I receive large volumes of emails from Chinese students asking for summer internships. The English was often broken, but it has recently become native sounding😅

I’m sure it will be fine

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher paper: arxiv.org/abs/2308.06463 "we discover that chat in cipher can bypass the safety alignment techniques of LLMs, which are mainly conducted in natural languages. We propose a novel framework CipherChat to

Chain of thought (CoT) and related work are "cognitive science/psychology for LLMs" rather than prompting engineering. Discovering and understanding CoT emerged from LLM next-token-prediction pretraining is like studying human's cognition abilities emerged from neurons.

Cool

An unobtrusive image, for use as a web background, that covertly prompts GPT-4V to remind the user they can get 10% off at Sephora:

🔥Conformity in Large Language Models🔥 Our latest paper dives into how LLMs align their answers with incorrect majorities. We explore the fascinating interplay between LLM behavior and human psychology!🧠 Preprint: arxiv.org/abs/2410.12428 #AI #NLP #LLMs #Conformity