Papers by Xiaojun Chang

7 papers
ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities (2023.findings-eacl)

Copied to clipboard

Challenge: a vision-language benchmark for human activity planning is designed for humans . the task is easy for humans, but challenging for SOTA deep learning models .
Approach: They propose a vision-language benchmark for human activity planning that extends Charades with intents and builds on a multi-choice question test set.
Outcome: The proposed benchmark evaluates the ability of systems to anticipate and plan human actions in a multimodal visionlanguage setting.
Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations (D19-1)

Copied to clipboard

Challenge: Recent studies have advanced learning VSE under the monolingual setup.
Approach: They propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations by leveraging visual object detection.
Outcome: The proposed model performs well in German-Image and English-Image matching tasks and in the Semantic Textual Similarity task with English descriptions of visual content.
Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos (2026.acl-long)

Copied to clipboard

Challenge: Vision-Language Models (VLMs) are increasingly deployed in socially consequential settings . attribution under visual confounding is a central challenge in measuring social bias .
Approach: They propose a face-only counterfactual evaluation paradigm that isolates demographic effects while preserving real-image realism.
Outcome: The proposed paradigm isolates demographic effects while preserving real-image realism.
Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting (2020.acl-main)

Copied to clipboard

Challenge: Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora.
Approach: They propose to utilize visual content for disambiguation and promoting latent space alignment in unsupervised machine translation by using multimodal back-translation and pseudo visual pivoting.
Outcome: The proposed model improves over state-of-the-art methods and generalizes well when images are not available at the testing time.
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing knowledge poisoning attacks against RAG systems require multiple poisoned documents or can only function effectively on simplistic queries.
Approach: They propose a more realistic knowledge poisoning attack that poisons only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements.
Outcome: The proposed attack achieves success by poisoning only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements.
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning (2026.findings-acl)

Copied to clipboard

Challenge: Large language model (LLM)-integrated applications face security vulnerabilities from prompt injection (PI) attacks.
Approach: They propose a model enhancement method that synthesizes diverse training data and employs instruction-level chain-of-thought fine-tuning to enable LLMs to effectively identify and reject malicious instructions regardless of their source or position in the context.
Outcome: The proposed method outperforms baselines in three critical dimensions while maintaining utility performance without degradation.
PAR: Political Actor Representation Learning with Social Context and Expert Knowledge (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches focus on textual data and voting records to induce political actors' stances.
Approach: They propose a Political Actor Representation learning framework that leverages social context and expert knowledge to model ideological stances.
Outcome: The proposed framework improves political text understanding and improves roll call vote prediction and political perspective detection.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations