🧑‍🔬 Xinyun Chen — all works

41 works · ← Xinyun Chen

1. Scaling Instruction-Finetuned Language Models ↗arXiv:2210.11416 · no summary yetHyung Won Chung et al.2022 · 3,392 citations
2. Delving into Transferable Adversarial Examples and Black-box Attacks ↗arXiv (Cornell University) · no summary yetYanpei Liu et al.2016 · 1,184 citations
3. Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning ↗arXiv (Cornell University) · no summary yetXinyun Chen et al.2017 · 1,011 citations
4. Large Language Models Can Be Easily Distracted by Irrelevant ContextarXiv:2302.00093Freda Shi, Xinyun Chen, Kanishka Misra, et al.2023 · 534 citations
5. Large Language Models as OptimizersarXiv:2309.03409Chengrun Yang, Xuezhi Wang, Yifeng Lu, et al.2023 · 413 citations
6. Large Language Models Cannot Self-Correct Reasoning YetarXiv:2310.01798Jie Huang, Xinyun Chen, Swaroop Mishra, et al.2023 · 412 citations
7. Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetMicah Goldblum et al.2020 · 361 citations
8. Larger language models do in-context learning differentlyarXiv:2303.03846Jerry Wei, Jason Wei, Yi Tay, et al.2023 · 285 citations
9. Adversarial Example Defense: Ensembles of Weak Defenses are not Strong ↗no summary yetWarren He et al.2017 · 206 citations
10. Towards Robustness of Text-to-SQL Models against Synonym SubstitutionAnnual Meeting of the Association for Computational Linguistics (ACL)Yujian Gan, Xinyun Chen, Qiuping Huang, et al.2021 · 143 citations
11. Tree-to-tree Neural Networks for Program Translation ↗arXiv:1802.03691 · no summary yetXinyun Chen, Chang Liu, Dawn Song2018 · 133 citations
12. Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models ↗arXiv:2310.06117 · no summary yetHuaixiu Steven Zheng et al.2023 · 126 citations
13. Large Language Models as Tool Makers ↗arXiv:2305.17126 · no summary yetTianle Cai et al.2023 · 123 citations
14. Exploring Underexplored Limitations of Cross-Domain Text-to-SQL GeneralizationConference on Empirical Methods in Natural Language Processing (EMNLP)Yujian Gan, Xinyun Chen, Matthew Purver2021 · 123 citations
15. Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension ↗International Conference on Learning Representations · no summary yetXinyun Chen et al.2020 · 116 citations
16. Natural SQL: Making SQL Easier to Infer from Natural Language Specifications ↗Findings of the Association for Computational Linguistics: EMNLP 2021 · no summary yetYujian Gan et al.2021 · 108 citations
17. Execution-Guided Neural Program Synthesis. ↗International Conference on Learning Representations · no summary yetXinyun Chen, Chang Liu, Dawn Xiaodong Song2018 · 93 citations
18. Universal Self-Consistency for Large Language Model GenerationarXiv:2311.17311Xinyun Chen, Renat Aksitov, Uri Alon, et al.2023 · 92 citations
19. Fooling Vision and Language Models Despite Localization and Attention Mechanism ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetXiaojun Xu et al.2018 · 90 citations
20. Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong ↗arXiv (Cornell University) · no summary yetWarren He et al.2017 · 76 citations
21. Large Language Models as Analogical Reasoners ↗arXiv:2310.01714 · no summary yetMichihiro Yasunaga et al.2023 · 74 citations
22. Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language ModelsarXiv:2305.14705Sheng Shen, Le Hou, Yanqi Zhou, et al.2023 · 70 citations
23. Symbol tuning improves in-context learning in language models ↗Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yetJerry Wei et al.2023 · 68 citations
24. Self-Discover: Large Language Models Self-Compose Reasoning Structures ↗arXiv:2402.03620 · no summary yetPei Zhou et al.2024 · 61 citations
25. Premise Order Matters in Reasoning with Large Language Models ↗arXiv:2402.08939 · no summary yetXinyun Chen et al.2024 · 58 citations
26. NATURAL PLAN: Benchmarking LLMs on Natural Language Planning ↗arXiv:2406.04520 · no summary yetHuaixiu Steven Zheng et al.2024 · 51 citations
27. LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs ↗International Conference on Machine Learning · no summary yetHongyu Ren et al.2021 · 49 citations
28. A Human-Inspired Reading Agent with Gist Memory of Very Long ContextsarXiv:2402.09727Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta, et al.2024 · 46 citations
29. On Memorization of Large Language Models in Logical ReasoningInternational Joint Conference on Natural Language Processing (IJCNLP)Chulin Xie, Yangsibo Huang, Chiyuan Zhang, et al.2025 · 45 citations
30. Towards Synthesizing Complex Programs from Input-Output Examples ↗arXiv (Cornell University) · no summary yetXinyun Chen, Chang Liu, Dawn Xiaodong Song2017 · 40 citations
31. BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models ↗arXiv:2308.16458 · no summary yetXiangru Tang et al.2023 · 38 citations
32. Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis ↗arXiv (Cornell University) · no summary yetKavi Gupta et al.2020 · 34 citations
33. SpreadsheetCoder: Formula Prediction from Semi-structured Context ↗arXiv:2106.15339 · no summary yetXinyun Chen et al.2021 · 31 citations
34. Transformers Can Achieve Length Generalization But Not Robustly ↗arXiv:2402.09371 · no summary yetYongchao Zhou et al.2024 · 29 citations
35. Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages ↗arXiv (Cornell University) · no summary yetXinyun Chen, Dawn Xiaodong Song, Yuandong Tian2021 · 17 citations
36. PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetXinyun Chen et al.2021 · 15 citations
37. Benchmarking Language Models for Code Syntax Understanding ↗Findings of the Association for Computational Linguistics: EMNLP 2022 · no summary yetDa Shen et al.2022 · 14 citations
38. SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs ↗arXiv:2110.14890 · no summary yetHongyu Ren et al.2021 · 11 citations
39. Learning Neural Programs To Parse Programs. ↗no summary yetXinyun Chen, Chang Liu, Dawn Xiaodong Song2017 · 4 citations
40. An End-to-End Approach for Natural Language to IFTTT Program Translation ↗no summary yetLiu Chang et al.2016 · 1 citation
41. ADVM'21 ↗ACM International Conference on Multimedia (ACM MM) · no summary yetAishan Liu et al.2021

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/xinyun-chen/works/