publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
The latest publication list can be found in my profile in Google Scholar.
2026
- arXivBIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric EnvironmentsarXiv preprint arXiv:2610.29426, Oct 2026
- arXivORCA: Evaluating LLMs on Data Science Code TranslationarXiv preprint arXiv:2609.30749, Sep 2026
- arXivImpossibleRubrics: Stress-Testing Generated Rubrics as Reward SignalsarXiv preprint arXiv:2609.16816, Sep 2026
- arXiv
- ACLLaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language ModelsIn Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026
- arXivAgent Retrieval Bench: Evaluating Repository Context Retrieval for Coding AgentsarXiv preprint arXiv:2607.24882, Jul 2026
- arXivDiff-SQL: SQL Efficiency Optimization via Patch Generation and Constraint AlignmentarXiv preprint arXiv:2610.06857, Jun 2026
- CVPRBeyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFTIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2026
- arXivHint Tuning: Less Data Makes Better ReasonersarXiv preprint arXiv:2605.08665, May 2026
- ICLRBIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic InteractionsIn International Conference on Learning Representations, Apr 2026
2025
- NeurIPSSWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World ApplicationsIn Advances in Neural Information Processing Systems, Dec 2025
- arXivFlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual QuestionsarXiv preprint arXiv:2509.17177, Sep 2025
- ACLFlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model EvaluationIn Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), Aug 2025
- ACLFlagEval-Arena: A Side-by-Side Comparative Evaluation Platform for Large Language Models and Text-Driven AIGCIn Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), Aug 2025
- arXivBeyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for InformationarXiv preprint arXiv:2508.11252, Aug 2025
- Are large language models ready for multi-turn tabular data analysis?In Forty-second International Conference on Machine Learning, Jul 2025
- ACL
- ACLMicro-Act: Mitigate Knowledge Conflict in Question Answering via Actionable Self-ReasoningIn Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2025
- arXivThe Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language ModelsarXiv preprint arXiv:2505.22017, May 2025
- AAAILegend: Leveraging Representation Engineering to Annotate Safety Margin for Preference DatasetsIn Proceedings of the AAAI Conference on Artificial Intelligence, 2025
- Conversational few-shot prompting: Rethinking few-shot prompting for chat language model2025
-
2024
- arXivTowards understanding the influence of reward margin on preference model performancearXiv preprint arXiv:2404.04932, 2024
- arXivTowards analyzing and understanding the limitations of DPO: A theoretical perspectivearXiv preprint arXiv:2404.04626, 2024
- ACLBefore generation, align it! A novel and effective strategy for mitigating hallucinations in text-to-sql generationIn Association for Computational Linguistics (ACL Findings), 2024
2023
- arXiv
- AAAIGraphix-t5: Mixing pre-trained transformers with graph-aware layers for text-to-sql parsingIn Proceedings of the AAAI Conference on Artificial Intelligence, 2023
- arXivFLM-101B: An open LLM and how to train it with $100k budgetarXiv preprint arXiv:2309.03852, 2023
- NeurIPSCan LLM already serve as a database interface? A big bench for large-scale database grounded text-to-sqlsIn Advances in Neural Information Processing Systems, 2023
2022
- KBSSdcup: Schema dependency-enhanced curriculum pre-training for table semantic parsingKnowledge-Based Systems, 2022
- ACLS^2 SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL ParsersIn Association for Computational Linguistics (ACL Findings), 2022
- COLINGSUN: Exploring intrinsic uncertainties in text-to-SQL parsersIn Proceedings of the 29th International Conference on Computational Linguistics, 2022
- SIGKDDProton: Probing schema linking information from pre-trained language models for text-to-sql parsingIn Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022
- arXivA survey on text-to-sql parsing: Concepts, methods, and future directionsarXiv preprint arXiv:2208.13629, 2022
2021
- IJFSFR–KDE: a hybrid fuzzy rule-based information fusion method with its application in biomedical classificationInternational Journal of Fuzzy Systems, 2021
- AAAIExploring auxiliary reasoning tasks for task-oriented dialog systems with meta cooperative learningIn Proceedings of the AAAI Conference on Artificial Intelligence, 2021
- InfoSciA fuzzy preference-based Dempster-Shafer evidence theory for decision fusionInformation Sciences, 2021
2019
- IJDSNAn improved method to determine basic probability assignment with interval number and its application in classificationInternational Journal of Distributed Sensor Networks, 2019
2018
- SensorsA Weighted Combination Method for Conflicting Evidence in Multi-Sensor Data FusionSensors, 2018
- IEEE AccessA Non-Parametric Method to Determine Basic Probability Assignment Based on Kernel Density EstimationIEEE Access, 2018