11 citations · 22 across the 8 of their papers we have counts for
9 papers
Articulation Upper Bounds for Language Models
Alexander Spangher, Daniel E. Ho, Diyi Yang +2
Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers. What, then, are the limits of language? We take steps towards measuri…
Dynamic Skill Adaptation for Large Language Models
Jiaao Chen, Diyi Yang
We present Dynamic Skill Adaptation (DSA), an adaptive and dynamic framework to adapt novel and complex skills to Large Language Models (LLMs). Compared with previous work which le…
Distilling an End-to-End Voice Assistant Without Instruction Training Data
William Held, Ella Li, Michael Ryan +3
Voice assistants, such as Siri and Google Assistant, typically model audio and text separately, resulting in lost speech information and increased complexity. Recent efforts to add…
Towards Social AI: A Survey on Understanding Social Interactions
Sangmin Lee, Minzhi Li, Bolin Lai +8
Social interactions form the foundation of human societies. Artificial intelligence has made significant progress in certain areas, but enabling machines to seamlessly understand s…
DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
Zhehao Zhang, Jiaao Chen, Diyi Yang
The current paradigm of evaluating Large Language Models (LLMs) through static benchmarks comes with significant limitations, such as vulnerability to data contamination and a lack…
A Safe Harbor for AI Evaluation and Red Teaming
Shayne Longpre, Sayash Kapoor, Kevin Klyman +20
Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by promi…
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
Yi Zeng, Hongpeng Lin, Jingwen Zhang +3
Most traditional AI safety research has approached AI models as machines and centered on algorithm-focused attacks developed by security experts. As large language models (LLMs) be…
Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach
Yanchen Liu, Mingyu Derek Ma, Wenna Qin +5
Susceptibility to misinformation describes the degree of belief in unverifiable claims, a latent aspect of individuals' mental processes that is not observable. Existing susceptibi…
Unlearn What You Want to Forget: Efficient Unlearning for LLMs
Jiaao Chen, Diyi Yang
Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data, however, this process might suffer from privacy is…