Xinyu Hu

39 papers A* 4A 2Journal 23Unranked 10
YearRankTypeTitle / Venue / Authors
2026 J jnl
CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria.
CoRR
Xinyu Hu, Yancheng He, Weixun Wang, Tao Feng, Li Lin, Jiashun Liu, Wenbo Su, Bo Zheng, Xiaojun Wan
2026 A* conf
SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs.
AAAI
Zhenliang Zhang, Xinyu Hu, Xiaojun Wan
2025 — conf
A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability.
ACL (1)
Xinyu Hu, Mingqi Gao, Li Lin, Zhenghan Yu, Xiaojun Wan
2025 J jnl
A Dual-Perspective NLG Meta-Evaluation Framework with Automatic Benchmark and Better Interpretability.
CoRR
Xinyu Hu, Mingqi Gao, Li Lin, Zhenghan Yu, Xiaojun Wan
2025 — conf
Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation.
NAACL (Long Papers)
Mingqi Gao, Xinyu Hu, Li Lin, Xiaojun Wan
2025 J jnl
Aspect-Guided Multi-Level Perturbation Analysis of Large Language Models in Automated Peer Review.
CoRR
Jiatao Li, Yanheng Li, Xinyu Hu, Mingqi Gao, Xiaojun Wan
2025 J jnl
CFunModel: A "Funny" Language Model Capable of Chinese Humor Generation and Processing.
CoRR
Zhenghan Yu, Xinyu Hu, Xiaojun Wan
2025 A* conf
DAMON: A Dialogue-Aware MCTS Framework for Jailbreaking Large Language Models.
EMNLP
Xu Zhang, Xunjian Yin, Dinghao Jing, Huixuan Zhang, Xinyu Hu, Xiaojun Wan
2025 — conf
Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models.
NAACL (Findings)
Jiatao Li, Xinyu Hu, Xunjian Yin, Xiaojun Wan
2025 A conf
Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models.
CIKM
Zhenliang Zhang, Junzhe Zhang, Xinyu Hu, Huixuan Zhang, Xiaojun Wan
2025 J jnl
Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models.
CoRR
Zhenliang Zhang, Junzhe Zhang, Xinyu Hu, Huixuan Zhang, Xiaojun Wan
2025 J jnl
Exploring the Multilingual NLG Evaluation Abilities of LLM-Based Evaluators.
CoRR
Jiayi Chang, Mingqi Gao, Xinyu Hu, Xiaojun Wan
2025 J jnl
HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy.
CoRR
Fan Xu, Xinyu Hu, Zhenghan Yu, Li Lin, Xu Zhang, Yang Zhang, Wei Zhou, Jinjie Gu, Xiaojun Wan
2025 — conf
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs.
ACL (1)
Zhenliang Zhang, Xinyu Hu, Huixuan Zhang, Junzhe Zhang, Xiaojun Wan
2025 J jnl
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs.
CoRR
Zhenliang Zhang, Xinyu Hu, Huixuan Zhang, Junzhe Zhang, Xiaojun Wan
2025 J jnl
LEDOM: An Open and Fundamental Reverse Language Model.
CoRR
Xunjian Yin, Sitao Cheng, Yuxi Xie, Xinyu Hu, Li Lin, Xinyi Wang, Liangming Pan, William Yang Wang, Xiaojun Wan
2025 — conf
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency.
ACL (Findings)
Junzhe Zhang, Huixuan Zhang, Xunjian Yin, Baizhou Huang, Xu Zhang, Xinyu Hu, Xiaojun Wan
2025 J jnl
Minos: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text.
CoRR
Junzhe Zhang, Huixuan Zhang, Xinyu Hu, Li Lin, Mingqi Gao, Shi Qiu, Xiaojun Wan
2025 J jnl
NeUQI: Near-Optimal Uniform Quantization Parameter Initialization.
CoRR
Li Lin, Xinyu Hu, Xiaojun Wan
2025 J jnl
Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning.
CoRR
Zihe Liu, Jiashun Liu, Yancheng He, Weixun Wang, Jiaheng Liu, Ling Pan, Xinyu Hu, Shaopan Xiong, Ju Huang, Jian Hu, Shengyi Huang, Siran Yang, Jiamang Wang, Wenbo Su, Bo Zheng
2025 — conf
Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference.
NAACL (Findings)
Mingqi Gao, Yixin Liu, Xinyu Hu, Xiaojun Wan, Jonathan Bragg, Arman Cohan
2025 J jnl
Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference.
CoRR
Mingqi Gao, Yixin Liu, Xinyu Hu, Xiaojun Wan, Jonathan Bragg, Arman Cohan
2025 J jnl
SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs.
CoRR
Zhenliang Zhang, Xinyu Hu, Xiaojun Wan
2025 — conf
Towards A "Novel" Benchmark: Evaluating Literary Fiction with Large Language Models.
ACL (Findings)
Wenqing Wang, Mingqi Gao, Xinyu Hu, Xiaojun Wan
2025 A conf
Where Do LLMs Go Wrong? Diagnosing Automated Peer Review via Aspect-Guided Multi-Level Perturbation.
CIKM
Jiatao Li, Yanheng Li, Xinyu Hu, Mingqi Gao, Xiaojun Wan
2024 J jnl
Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation.
CoRR
Mingqi Gao, Xinyu Hu, Li Lin, Xiaojun Wan
2024 — conf
Are LLM-based Evaluators Confusing NLG Quality Criteria?
ACL (1)
Xinyu Hu, Mingqi Gao, Sen Hu, Yang Zhang, Yicheng Chen, Teng Xu, Xiaojun Wan
2024 J jnl
Are LLM-based Evaluators Confusing NLG Quality Criteria?
CoRR
Xinyu Hu, Mingqi Gao, Sen Hu, Yang Zhang, Yicheng Chen, Teng Xu, Xiaojun Wan
2024 — conf
Error-Robust Retrieval for Chinese Spelling Check.
LREC/COLING
Xunjian Yin, Xinyu Hu, Jin Jiang, Xiaojun Wan
2024 J jnl
Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models.
CoRR
Jiatao Li, Xinyu Hu, Xunjian Yin, Xiaojun Wan
2024 J jnl
LLM-based NLG Evaluation: Current Status and Challenges.
CoRR
Mingqi Gao, Xinyu Hu, Jie Ruan, Xiao Pu, Xiaojun Wan
2024 J jnl
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency.
CoRR
Junzhe Zhang, Huixuan Zhang, Xunjian Yin, Baizhou Huang, Xu Zhang, Xinyu Hu, Xiaojun Wan
2024 J jnl
SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval.
CoRR
Jiatao Li, Xinyu Hu, Xiaojun Wan
2024 A* conf
Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability.
EMNLP
Xinyu Hu, Li Lin, Mingqi Gao, Xunjian Yin, Xiaojun Wan
2024 J jnl
Themis: Towards Flexible and Interpretable NLG Evaluation.
CoRR
Xinyu Hu, Li Lin, Mingqi Gao, Xunjian Yin, Xiaojun Wan
2023 — conf
Exploring Context-Aware Evaluation Metrics for Machine Translation.
EMNLP (Findings)
Xinyu Hu, Xunjian Yin, Xiaojun Wan
2023 A* conf
Exploring Discourse Structure in Document-level Machine Translation.
EMNLP
Xinyu Hu, Xiaojun Wan
2023 J jnl
RST Discourse Parsing as Text-to-Text Generation.
IEEE ACM Trans. Audio Speech Lang. Process.
Xinyu Hu, Xiaojun Wan
2022 J jnl
Chinese Spelling Check with Nearest Neighbors.
CoRR
Xunjian Yin, Xinyu Hu, Xiaojun Wan