Publications
My advisees*. Equal contribution^.
2025
-
PreprintRevisiting Prompt Optimization with Large Reasoning Models-A Case Study on Event ExtractionarXiv preprint arXiv:2504.07357, 2025
-
PreprintFailure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound OnesarXiv preprint arXiv:2507.00322, 2025
-
Preprint
-
PreprintReassessing Code Authorship Attribution in the Era of Language ModelsarXiv preprint arXiv:2506.17120, 2025
-
PreprintGuiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code GenerationarXiv preprint arXiv:2506.23034, 2025
-
EMNLP’25Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language ModelsarXiv preprint arXiv:2505.15634 (to appear at EMNLP 2025 Main), 2025
-
EMNLP’25All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other TokensTo appear at EMNLP 2025 Main, 2025
-
EMNLP’25 FindingsA survey on sparse autoencoders: Interpreting the internal mechanisms of large language modelsarXiv preprint arXiv:2503.05613 (to appear at EMNLP 2025 Findings), 2025
-
EMNLP’25 FindingsBeneath the Surface: How Large Language Models Reflect Hidden BiasarXiv preprint arXiv:2502.19749 (to appear at EMNLP 2025 Findings), 2025
-
COLM’25WCan LLMs Simulate Personas with Reversed Performance? A Benchmark for Counterfactual Instruction FollowingCOLM Workshop on Social Simulation with LLMs, 2025
-
IROS’25Autospatial: Visual-language reasoning for social robot navigation through efficient spatial reasoning learningarXiv preprint arXiv:2503.07557 (to appear at IROS 2025), 2025
-
AAAI’25WMechanistic Understanding of Language Models in Syntactic Code CompletionAAAI Workshop on Towards Knowledgeable Foundation Models, 2025
-
ICLR’25DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories SearchThe Thirteenth International Conference on Learning Representations, 2025
-
AAAI’25WMathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education(Invited Presentation at Wolfram Research LLM Agent Colloquium)AAAI AI4Edu Workshop, 2025
2024
-
PreprintUnderstanding the Effect of Algorithm Transparency of Model Explanations in Text-to-SQL Semantic ParsingarXiv preprint arXiv:2410.16283, 2024
-
EMNLP’24
-
ACL’24An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs(Covered by MIT Technology Review China [English Translate])ACL, 2024
-
Preprint
-
ICLR’24Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning(Featured in Hugging Face Daily Papers)The Twelfth International Conference on Learning Representations (also at ICLR Workshop on Reliable and Responsible Foundation Models), 2024
2023
-
ACL’23Improving Generalization in Language Model-based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-based Techniques(Rank#8 on Spider leaderboard as of Aug 2023)In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2023
-
AAAI’23 SAExplaining Large Language Model-Based Neural Semantic Parsers (Student Abstract)AAAI Student Abstract, 2023
-
JBP’23A paradigm shift from “human writing” to “machine generation” in personality test development: An application of state-of-the-art natural language processing(Editor Commendation, one of 13 out of 1,000+ submissions in 2022)Journal of Business and Psychology, 2023
2022
-
ICLR’22 DL4CodeCode Editing from Few Exemplars by Adaptive Multi-Extent CompositionIn Deep Learning for Code Workshop at International Conference on Learning Representations, 2022
2021
-
DissertationOn Advancing Natural Language Interfaces: Data Collection, Model Development, and User Interaction2021
2020
2019
-
EMNLP-IJCNLP’19
2018
-
KDD’18 DL Day
2016
-
AAAI’16Semi-supervised multinomial naive bayes for text classification by leveraging word-level statistical constraintIn Proceedings of the AAAI Conference on Artificial Intelligence, 2016