Zhixue Zhao

19 papers · 2022–2026 · 7 conferences · across top CS/AI conferences

Achievements

+6 more ↓

🗺️ Taxonomy Completionist (36) 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (15)

❓ The Questioner (3) 📈 Trend Setter ⚡ Prolific Year (12) 💎 Century Club (15) 🗃️ Keyword Collector (89) 🔥 Unstoppable (5)

Conferences

EMNLP (6) ACL (3) NAACL (3) AAAI (2) EACL (2) ICML (2) ICLR (1)

Top co-authors

Nikolaos Aletras (4) Jörg Schlötterer (3) Christin Seifert (3) Paul Youssef (3) Yue Li (3) Huan Zhao (2) Guanghui Ye (2) Xupeng Zha (2) Carolina Scarton (2) Zhihua Jiang (2)

Research topics

Understanding (1)

Keywords

feature attribution (3) in-context learning (3) large language model (2) model interpretability (2) multilingual model (2) model explanation (2) efficient inference (1) natural language inference (1) zero-shot learning (1) text-to-image generation (1) multimodal interaction (1) image editing (1) text classification (1) model editing (1) adversarial classification (1) emotion recognition (1) model pruning (1) label selection (1) low-resource language (1) dialogue generation (1)

Papers

Seeing All Sides: Multi-Perspective In-Context Learning for Subjective NLP EACL 2026 Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering AAAI 2026 Making Visual Dialogue More Engaging: A New Task, Method, and Metric AAAI 2026 KidsArtBench: Multi-Dimensional Children’s Art Evaluation with Attribute-Aware MLLMs EACL 2026 It’s All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs EMNLP 2025 Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? EMNLP 2025 Label Set Optimization via Activation Distribution Kurtosis for Zero-Shot Classification with Generative Models EMNLP 2025 Revisiting Pruning vs Quantization for Small Language Models EMNLP 2025 RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning ICML 2025 Position: Editing Large Language Models Poses Serious Safety Risks ICML 2025 Has this Fact been Edited? Detecting Knowledge Edits in Language Models NAACL 2025 How to Make LLMs Forget: On Reversing In-Context Knowledge Edits NAACL 2025 ScImage: How good are multimodal large language models at scientific text-to-image generation? ICLR 2025 Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language Models ACL 2025 Explainable Hallucination through Natural Language Inference Mapping ACL 2025 Minimal, Local, and Robust: Embedding-Only Edits for Implicit Bias in T2I Models EMNLP 2025 Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models NAACL 2024 Incorporating Attribution Importance for Improving Faithfulness Metrics ACL 2023 On the Impact of Temporal Concept Drift on Model Explanations EMNLP 2022