9 citations · 30 across the 15 of their papers we have counts for
15 papers
Embracing AI in Education: Understanding the Surge in Large Language Model Use by Secondary Students
Tiffany Zhu, Kexun Zhang, William Yang Wang
The impressive essay writing and problem-solving capabilities of large language models (LLMs) like OpenAI's ChatGPT have opened up new avenues in education. Our goal is to gain ins…
Scaling LLM Inference with Optimized Sample Compute Allocation
Kexun Zhang, Shang Zhou, Danqing Wang +2
Sampling is a basic operation in many inference-time algorithms of large language models (LLMs). To scale up inference efficiently with a limited compute, it is crucial to find an…
SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
Antonis Antoniades, Albert Örwall, Kexun Zhang +3
Software engineers operating in complex and dynamic environments must continuously adapt to evolving requirements, learn iteratively from experience, and reconsider their approache…
Human Bias in the Face of AI: Examining Human Judgment Against Text Labeled as AI Generated
Tiffany Zhu, Iain Weissburg, Kexun Zhang +1
As AI advances in text generation, human trust in AI generated content remains constrained by biases that go beyond concerns of accuracy. This study explores how bias shapes the pe…
Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
Xinyi Wang, Antonis Antoniades, Yanai Elazar +4
The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing v…
Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions
Kexun Zhang, Yee Man Choi, Zhenqiao Song +3
How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform we…
Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation
Xinyi Wang, Alfonso Amayuelas, Kexun Zhang +3
Pre-trained language models (LMs) are able to perform complex reasoning without explicit fine-tuning. To understand how pre-training with a next-token prediction objective contribu…
Zero-Shot Detection of Machine-Generated Codes
Xianjun Yang, Kexun Zhang, Haifeng Chen +3
This work proposes a training-free approach for the detection of LLMs-generated codes, mitigating the risks associated with their indiscriminate usage. To the best of our knowledge…
Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding
Kexun Zhang, Hongqiao Chen, Lei Li +1
Instruction-tuned large language models (LLMs) excel at many tasks but often fail to use external tools due to complicated and unfamiliar syntax constraints. While extensive fine-t…
Invisible Image Watermarks Are Provably Removable Using Generative AI
Xuandong Zhao, Kexun Zhang, Zihao Su +6
Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated…
Large Language Models Are Partially Primed in Pronoun Interpretation
Suet-Ying Lam, Qingcheng Zeng, Kexun Zhang +2
While a large body of literature suggests that large language models (LLMs) acquire rich linguistic representations, little is known about whether they adapt to linguistic biases i…
ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers
Kexun Zhang, Danqing Wang, Jingtao Xia +2
Large language models (LLMs) excel at implementing code from functionality descriptions but struggle with algorithmic problems that require not only implementation but also identif…
ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval
Kexun Zhang, Xianjun Yang, William Yang Wang +1
Diffusion models show promising generation capability for a variety of data. Despite their high generation quality, the inference for diffusion models is still time-consuming due t…
A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation
Kexun Zhang, Rui Wang, Xu Tan +4
It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, whi…
WSRGlow: A Glow-based Waveform Generative Model for Audio Super-Resolution
Kexun Zhang, Yi Ren, Changliang Xu +1
Audio super-resolution is the task of constructing a high-resolution (HR) audio from a low-resolution (LR) audio by adding the missing band. Previous methods based on convolutional…