13 citations · 34 across the 9 of their papers we have counts for
9 papers
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
Kaixuan Huang, Jiacheng Guo, Zihao Li +15
Large language models have demonstrated impressive performance on challenging mathematical reasoning tasks, which has triggered the discussion of whether the performance is achieve…
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
Yukang Yang, Declan Campbell, Kaixuan Huang +3
Many recent studies have found evidence for emergent reasoning capabilities in large language models (LLMs), but debate persists concerning the robustness of these capabilities, an…
A Theoretical Perspective for Speculative Decoding Algorithm
Ming Yin, Minshuo Chen, Kaixuan Huang +1
Transformer-based autoregressive sampling has been the major bottleneck for slowing down large language model inferences. One effective way to accelerate inference is \emph{Specula…
AI Risk Management Should Incorporate Both Safety and Security
Xiangyu Qi, Yangsibo Huang, Yi Zeng +22
The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety…
SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
Kaixuan Huang, Xudong Guo, Mengdi Wang
Speculative decoding reduces the inference latency of a target large language model via utilizing a smaller and faster draft model. Its performance depends on a hyperparameter K --…
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Boyi Wei, Kaixuan Huang, Yangsibo Huang +6
Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This stu…
Scaling In-Context Demonstrations with Structured Attention
Tianle Cai, Kaixuan Huang, Jason D. Lee +1
The recent surge of large language models (LLMs) highlights their ability to perform in-context learning, i.e., "learning" to perform a task from a few demonstrations in the contex…
Visual Adversarial Examples Jailbreak Aligned Large Language Models
Xiangyu Qi, Kaixuan Huang, Ashwinee Panda +3
Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This…
Deep Reinforcement Learning for Cost-Effective Medical Diagnosis
Zheng Yu, Yikuan Li, Joseph Kim +3
Dynamic diagnosis is desirable when medical tests are costly or time-consuming. In this work, we use reinforcement learning (RL) to find a dynamic policy that selects lab test pane…