Jinxin Liu

Orcid: 0009-0009-4673-9824

Affiliations:
  • Tsinghua University, Department of Computer Science and Technology, Beijing, China


According to our database1, Jinxin Liu authored at least 14 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
MM-THEBench: Do Reasoning MLLMs Think Reasonably?
CoRR, January, 2026

2025
WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection.
CoRR, October, 2025

How does Transformer Learn Implicit Reasoning?
CoRR, May, 2025

ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation.
CoRR, March, 2025

Dynamic multi teacher knowledge distillation for semantic parsing in KBQA.
Expert Syst. Appl., 2025

AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.2, 2025

2024
Probing Structured Semantics Understanding and Generation of Language Models via Question Answering.
CoRR, 2024


DiaKoP: Dialogue-based Knowledge-oriented Programming for Neural-symbolic Knowledge Base Question Answering.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023
Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction.
CoRR, 2023

Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022
ConstGCN: Constrained Transmission-based Graph Convolutional Networks for Document-level Relation Extraction.
CoRR, 2022

ParaMac: A General Unsupervised Paraphrase Generation Framework Leveraging Semantic Constraints and Diversifying Mechanisms.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022


  Loading...