Profiles2020-2026
Derek Fai Wong
University of Macau
Also published as Derek F Wong
45Papers
14Last author
94Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers45
- ExGRPO: Learning to Reason from ExperienceAuthor 7 of 8ICLR 2026 · 51 citations
- Probing Semantic Alignment, Lexical Invariance, and Syntactic Influence in LLM Metaphor ProcessingAuthor 4 of 4ACL 2026 · 7 citations
- VisAidMath: Benchmarking Visual-Aided Mathematical ReasoningAuthor 7 of 7ACL 2026 · 6 citations
- Neuron-Aware Data Selection in Instruction Tuning for Large Language ModelsAuthor 9 of 9ICLR 2026 · 2 citations
- From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAGAuthor 7 of 7ACL Findings 2026 · 1 citation
- G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom AlignmentAuthor 6 of 6ACL 2026 · 1 citation
- Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QAAuthor 8 of 8ACL Findings 2026
- EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional UnderstandingAuthor 5 of 5ACL 2026
- Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine TranslationAuthor 10 of 10AAAI 2026
- MAKI: Multi-layer Aligned Knowledge Injection for Structure-aware Knowledge Graph Completion with Large Language ModelsAuthor 4 of 5ACL Findings 2026
- Poller: Are LLMs Suitable for Evaluating Poetry Understanding Task?Author 2 of 4ACL Findings 2026
- ToolRM: Towards Agentic Tool-Use Reward ModelingAuthor 7 of 9ACL Findings 2026
- Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance BoostAuthor 6 of 6NeurIPS 2025 · 6 citations
- Path Drift in Large Reasoning Models: How First-Person Commitments Override SafetyAuthor 5 of 5EMNLP 2025 · 3 citations
- Exploring the Impact of Personality Traits on LLM Bias and ToxicityAuthor 6 of 7EMNLP 2025 · 2 citations
- HiMATE: A Hierarchical Multi-Agent Framework for Machine Translation EvaluationAuthor 6 of 6EMNLP Findings 2025 · 2 citations
- Rethinking Prompt-based Debiasing in Large Language ModelAuthor 6 of 7ACL Findings 2025 · 2 citations
- Benchmarking the Detection of LLMs-Generated Modern Chinese PoetryAuthor 6 of 6EMNLP Findings 2025 · 1 citation
- Evaluation of Text-to-Image Generation from a Creativity PerspectiveAuthor 4 of 4EMNLP Findings 2025 · 1 citation
- CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and TaskAuthor 4 of 7EMNLP Findings 2025
- DelTA: An Online Document-Level Translation Agent Based on Multi-Level MemoryAuthor 4 of 7ICLR 2025
- SGIC: A Self-Guided Iterative Calibration Framework for RAGAuthor 5 of 5ACL 2025
- Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed AcceptanceAuthor 7 of 8EMNLP 2025
- SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-ReflectionAuthor 3 of 7NeurIPS 2024 · 49 citations
- Anchor-based Large Language ModelsAuthor 3 of 6ACL Findings 2024 · 9 citations
- Towards Demonstration-Aware Large Language Models for Machine TranslationAuthor 5 of 6ACL Findings 2024 · 2 citations
- CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent CooperationAuthor 3 of 5EMNLP 2024 · 1 citation
- Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine TranslationAuthor 5 of 6ACL Findings 2024 · 1 citation
- FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language ModelsAuthor 3 of 7ACL Findings 2024 · 1 citation
- Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language ModelAuthor 3 of 6ACL Findings 2024 · 1 citation
Showing the 30 most recent indexed papers.
