511 citations · 1.4k across the 31 of their papers we have counts for
15 papers · 1 filter
The Widespread Adoption of Large Language Model-Assisted Writing Across Society
Weixin Liang, Yaohui Zhang, Mihai Codreanu +3
The recent advances in large language models (LLMs) attracted significant public and policymaker interest in its adoption patterns. In this paper, we systematically analyze LLM-ass…
Adaptive Self-improvement LLM Agentic System for ML Library Development
Genghan Zhang, Weixin Liang, Olivia Hsu +1
ML libraries, often written in architecture-specific programming languages (ASPLs) that target domain-specific architectures, are key to efficient ML systems. However, writing thes…
LMFusion: Adapting Pretrained Language Models for Multimodal Generation
Weijia Shi, Xiaochuang Han, Chunting Zhou +4
We present LMFusion, a framework for empowering pretrained text-only large language models (LLMs) with multimodal generative capabilities, enabling them to understand and generate…
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
Weixin Liang, Lili Yu, Liang Luo +8
The development of large language models (LLMs) has expanded to multi-modal systems capable of processing text, images, and speech within a unified framework. Training these models…
Mapping the Increasing Use of LLMs in Scientific Papers
Weixin Liang, Yaohui Zhang, Zhengxuan Wu +11
Scientific publishing lays the foundation of science by disseminating research findings, fostering collaboration, encouraging reproducibility, and ensuring that scientific knowledg…
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
Weixin Liang, Zachary Izzo, Yaohui Zhang +9
We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum l…
GPT detectors are biased against non-native English writers
Weixin Liang, Mert Yuksekgonul, Yining Mao +2
The rapid adoption of generative language models has brought about substantial advancements in digital communication, while simultaneously raising concerns regarding the potential…
SEAL : Interactive Tool for Systematic Error Analysis and Labeling
Nazneen Rajani, Weixin Liang, Lingjiao Chen +2
With the advent of Transformers, large language models (LLMs) have saturated well-known NLP benchmarks and leaderboards with high aggregate performance. However, many times these m…
GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language
Zhiying Zhu, Weixin Liang, James Zou
Helping end users comprehend the abstract distribution shifts can greatly facilitate AI deployment. Motivated by this, we propose a novel task, dataset explanation. Given two image…
Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
Weixin Liang, Yuhui Zhang, Yongchan Kwon +2
We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (e.g. images and…
HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations
Weixin Liang, Kai-Hui Liang, Zhou Yu
Open-domain dialog systems have a user-centric goal: to provide humans with an engaging conversation experience. User engagement is one of the most important metrics for evaluating…
GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering
Weixin Liang, Yanhao Jiang, Zixuan Liu
Images are more than a collection of objects or attributes -- they represent a web of relationships among interconnected objects. Scene Graph has emerged as a new modality for a st…
LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering
Weixin Liang, Feiyang Niu, Aishwarya Reganti +2
The predominant approach to visual question answering (VQA) relies on encoding the image and question with a "black-box" neural encoder and decoding a single token as the answer li…
ALICE: Active Learning with Contrastive Natural Language Explanations
Weixin Liang, James Zou, Zhou Yu
Training a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes…
Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation
Weixin Liang, James Zou, Zhou Yu
Open Domain dialog system evaluation is one of the most important challenges in dialog research. Existing automatic evaluation metrics, such as BLEU are mostly reference-based. The…