Get started
Author

Kai-Wei Chang

Learn to Explain: Multimodal Reasoning Via Thought Chains for Science Question Answering
2022 · Pan Lu, Swaroop Mishra, et al. · neural information processing systems · 419
PDF
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
2023 · Pan Lu, Baolin Peng, et al. · neural information processing systems · 141
PDF
AVIS: Autonomous Visual Information Seeking with Large Language Model Agent
2023 · Ziniu Hu, Ahmet Iscen, et al. · neural information processing systems · 18
PDF
DesCo: Learning Object Recognition with Rich Language Descriptions
2023 · Liunian Li, Zi-Yi Dou, et al. · neural information processing systems · 12
PDF
SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA)
2026 · Liang-Chih Yu, Jonas Becker, et al. · International Workshop on Semantic Evaluation (SemEval) · 3
PDF
A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
2023 · Kareem Ahmed, Kai-Wei Chang, et al. · neural information processing systems · 2
PDF
BLUR: A Bi-Level Optimization Approach for LLM Unlearning
2026 · Hadi Reisizadeh, Jinghan Jia, et al. · Conference of the European Chapter of the Association for Computational Linguistics · 1
PDF
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks
2026 · Hyeonjeong Ha, Qiusi Zhan, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 1
Controllable Text Generation with Neurally-Decomposed Oracle
2022 · Tao Meng, Sidi Lu, et al. · neural information processing systems · 1
VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
SWAN: Semantic Watermarking with Abstract Meaning Representation
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
AutoSUIT Bench - Automated Security UnIt Test Benchmark for LLM Coding
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
Beyond Facts- Benchmarking Distributional Reading Comprehension in Large Language Models
2026 · Association for Computational Linguistics 2026, An Tsai, Ya, et al. · Underline Science Inc.
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks
2026 · Association for Computational Linguistics 2026, Bralios, Dimitrios, et al. · Underline Science Inc.
BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
2026 · Association for Computational Linguistics 2026, Chang, Kai-Wei, et al. · Underline Science Inc.
Inference-Time Control for Trustworthy Large Language Models
2026 · Yuyang Bai, Zheyuan Liu, et al. · Preprints.org
Open-Domain Safety Policy Construction
2026 · Di Wu, Siyue Liu, et al. · Findings of the Association for Computational Linguistics: EACL
PDF
BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation
2026 · Tsung-Min Pai, Jui-I Wang, et al. · Conference of the European Chapter of the Association for Computational Linguistics
PDF
SWAN: Semantic Watermarking with Abstract Meaning Representation
2026 · Ziping Ye, Gourab Dey, et al. · Annual Meeting of the Association for Computational Linguistics (ACL)
PDF
From Narrow Unlearning to Emergent Misalignment in LLMs
2026 · Erum Mushtaq, Anil Ramakrishna, et al. · Annual Meeting of the Association for Computational Linguistics (ACL)
PDF
Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society
2026 · Zheyuan Liu, Yixin Wan, et al. · Annual Meeting of the Association for Computational Linguistics (ACL)
PDF
Works count: 34
Citation count: 594
H-index: 4
I10-index: 4
Year
Topic
Type