Jiaang Li

I'm an ELLIS PhD student at the Pioneer Centre for Artificial Intelligence. I'm honored to be advised by Prof. Serge Belongie at the University of Copenhagen and Ivan Vulić at the University of Cambridge . Previously I spent two wonderful years at CoAStaL, advised by Prof. Anders Søgaard, and received my Master's degree in Computer Science at the University of Copenhagen.

Email  /  Google Scholar  /  Twitter  /  Github

profile photo
Research

My interests revolve around the convergence of natural language processing and computer vision, with a focus on gaining insights from human cognition. I am enthusiastic about exploring language grounding within multimodal contexts and investigating the linguistic and cognitive characteristics of models.

News
Publications & Preprints
* denotes equal contribution
Paper Image

Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
Jiaang Li, Yova Kementchedjhieva, Constanza Fierro, Anders Søgaard
TACL
code & data

TL;DR Our experiments show that LMs partially converge towards representations isomorphic to those of vision models, subject to dispersion, polysemy, and frequency, which has important implications for both multi-modal processing and the LM understanding debate.

Paper Image

FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture
Wenyan Li, Xinyu Zhang, Jiaang Li, Qiwei Peng, Raphael Tang, Li Zhou, Weijia Zhang, Guimin Hu, Yifei Yuan, Anders Søgaard, Daniel Hershcovich, Desmond Elliottd
EMNLP 2024
code  /  data

TL;DR In this work, we introduce FoodieQA, a manually curated, fine-grained image-text dataset capturing the intricate features of food cultures across various regions in China, and evaluates vision-language Models (VLMs) and large language models (LLMs) on newly collected, unseen food images and corresponding questions.

Paper Image

Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning
Wenyan Li, Jiaang Li, Rita Ramos, Raphael Tang, Desmond Elliottd
ACL 2024
code

TL;DR We analyze the robustness of a retrieval-augmented captioning model SmallCap and propose to train the model by sampling retrieved captions from more diverse sets, which decreases the chance that the model learns to copy majority tokens, and improves both in-domain and cross-domain performance.

Paper Image

Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing
Yong Cao, Wenyan Li, Jiaang Li, Yifei Yuan, Daniel Hershcovich
Preprint 2024

TL;DR We empirically show that GPT-4V excels at identifying cultural concepts but still exhibits weaker performance in low-resource languages, such as Tamil and Swahili, suggesting a promising solution for future visual cultural benchmark construction.

Paper Image

Structural Similarities Between Language Models and Neural Response Measurements
Jiaang Li*, Antonia Karamolegkou*, Yova Kementchedjhieva, Mostafa Abdou, Sune Lehmann, Anders Søgaard
NeurReps @ NeurIPS 2023
code

TL;DR This work shows that the larger neural language models get, the more their representations are structurally similar to neural response measurements from brain imaging.

Paper Image

Copyright Violations and Large Language Models
Antonia Karamolegkou*, Jiaang Li*, Li Zhou, Anders Søgaard
EMNLP 2023
code

TL;DR We explore the issue of copyright violations and large language models through the lens of verbatim memorization, focusing on possible redistribution of copyrighted text.

Paper Image

PokemonChat: Auditing ChatGPT for Pokemon Universe Knowledge
Laura Cabello, Jiaang Li, Ilias Chalkidis
Preprint 2023

TL;DR We probe ChatGPT for its conversational understanding and introduces a conversational framework (protocol) that can be adopted in future studies to assess ChatGPT's ability to generalize, combine features, and to acquire and reason over newly introduced knowledge from human feedback.

Services
  • Reviewer: ACL 2024, NLLP workshop' 2023

Stolen from Jon Barron. Big thanks!