Publications
Publications from time to time
2024
- Mercury: An Efficiency Benchmark for LLM Code SynthesisConference on Neural Information Processing Systems 2024
- Counseling Responses for Mental Health Forum Questions with Early Maladaptive Schema PredictionEuropean Conference on Artificial Intelligence 2024
- Rethinking the Influence of Source Code on Test Case GenerationarXiv preprint arXiv:2402.07844 2024
- CodeArena: A Dynamic Evaluation Framework for Code GenerationarXiv preprint 2024
- Committee:Mitigating Language Model Bias via Weak SupervisionarXiv preprint 2024
- Chain-of-Thought Improves Text Generation with Citations in Large Language ModelsIn Proceedings of the AAAI Conference on Artificial Intelligence 2024
2023
- Constituency-Informed and Constituency-Constrained Extractive Question Answering with Heterogeneous Graph Transformer2023
- Identifying Checkworthy Cure Claims on TwitterIn Proceedings of the ACM Web Conference 2023 2023
- Generating Reflective Questions for Engaging Gallery Visitors in ArtMuseIn Proceedings of the AAAI Conference on Artificial Intelligence 2023
- From Static to Dynamic: A Continual Learning Framework for Large Language ModelsarXiv preprint arXiv:2310.14248 2023
- Debiasing Language Models Using Energy-Guided Ordinary Differential EquationsOpenreview id:kaFrlUcAn3 2023
2022
- NUS-IDS at CheckThat! 2022: identifying check-worthiness of tweets using CheckthaT5Working Notes of CLEF 2022
- Image Semantic Relation GenerationarXiv preprint arXiv:2210.11253 2022