Papers by Zihao Yu
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)
Copied to clipboard
Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin
| Challenge: | a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities . |
| Approach: | They present a comparative analysis to identify and distinguish LLM activities from human activities. |
| Outcome: | The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities. |
MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills (2026.eacl-long)
Copied to clipboard
Zonghai Yao, Zihao Zhang, Chaolong Tang, Xingyu Bian, Youxia Zhao, Zhichao Yang, Junda Wang, Huixue Zhou, Won Seok Jang, Feiyun Ouyang, Hong Yu
| Challenge: | Current clinical LLM benchmarks fail to evaluate advanced clinical skills in AI and large language models (LLMs). |
| Approach: | They propose a framework to evaluate large language models (LLMs) using two instruction-following tasks designed to reflect real clinical scenarios. |
| Outcome: | The proposed framework evaluates LLMs through two instruction-following tasks designed to reflect real clinical scenarios. |
OpenHuEval: Evaluating Large Language Model on Hungarian Specifics (2025.findings-acl)
Copied to clipboard
Haote Yang, Xingjian Wei, Jiang Wu, Noémi Ligeti-Nagy, Jiaxing Sun, Yinfan Wang, Győző Zijian Yang, Junyuan Gao, Jingchao Wang, Bowen Jiang, Shasha Wang, Nanjun Yu, Zihao Zhang, Shixin Hong, Hongwei Liu, Wei Li, Songyang Zhang, Dahua Lin, Lijun Wu, Gábor Prószéky, Conghui He
| Challenge: | Recent advances in Large Language Models (LLMs) represent significant strides toward artificial general intelligence (AGI). |
| Approach: | They introduce OpenHuEval, the first benchmark for LLMs focusing on the Hungarian language and specifics. |
| Outcome: | The framework reveals intrinsic patterns and mechanisms of LLMs in non-English languages, with Hungarian serving as an example. |
A Survey on LLM-based Conversational User Simulation (2026.eacl-long)
Copied to clipboard
Bo Ni, Yu Wang, Leyao Wang, Branislav Kveton, Franck Dernoncourt, Yu Xia, Hongjie Chen, Reuben Luera, Samyadeep Basu, Subhojyoti Mukherjee, Puneet Mathur, Nesreen K. Ahmed, Junda Wu, Li Li, Huixin Zhang, Ruiyi Zhang, Tong Yu, Sungchul Kim, Jiuxiang Gu, Zhengzhong Tu, Alexa Siu, Zichao Wang, Seunghyun Yoon, Nedim Lipka, Namyong Park, Zihao Lin, Trung Bui, Yue Zhao, Tyler Derr, Ryan A. Rossi
| Challenge: | Recent advances in large language models (LLMs) have enabled high-fidelity generation of synthetic user conversation. |
| Approach: | They propose a taxonomy covering user granularity and simulation objectives . they analyze core techniques and evaluation methodologies to help them understand the latest developments . |
| Outcome: | The proposed model enables high-fidelity generation of synthetic user conversation. |
Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations (2026.acl-long)
Copied to clipboard
Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu
| Challenge: | Large Language Models generate outputs that extend beyond established knowledge . prior work does not characterize the unverifiable space as a whole . |
| Approach: | They propose a novelty-verifiability characterization that distinguishes Creative Synthesis from Groundless Fabrication by a conceptual creation task. |
| Outcome: | The proposed model distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Regium B) it shows that Region A is non-negligible and robust, persisting across generation strategies, models, domains, and embedding choices. |
Eliciting Implicit Acoustic Styles from Open-domain Instructions to Facilitate Fine-grained Controllable Generation of Speech (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current work relies on pre-defined rules or templates to control the style of speech. |
| Approach: | They propose to use open-domain instructions to generate speech with the acoustic style that meets users’ needs based on their instructions. |
| Outcome: | The proposed model can be used to generate speech with the acoustic style that meets users’ needs based on open-domain instructions. |
Generative Music Models’ Alignment with Professional and Amateur Users’ Expectations (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent years have witnessed rapid advances in text-to-music generation using large language models. |
| Approach: | They propose a task to align AI-generated music with human expressions . they use a dataset of over 1.5 million songs to analyze their content . |
| Outcome: | The proposed framework outperforms baseline models and facilitates end-to-end generation of songs audio. |
Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching (2026.acl-long)
Copied to clipboard
Bo Lv, Jingbo Sun, Jianwei Lv, Chen Tang, Shaojie Zhang, Nayu Liu, Guoxin Yu, Zihao Li, Qichao Zhang, Dongbin Zhao, Ping Luo, Yue Yu
| Challenge: | Existing routing methods rely on direct mapping from queries to models based on surface-level features, leading to poor generalizability on out-of-distribution data. |
| Approach: | They propose a new routing framework that recasts the routing task as a matching process of sifting similar queries from historical logs. |
| Outcome: | The proposed framework improves matching accuracy while lowering inference costs . it decouples linguistic surface forms from task-intrinsic requirements . |
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory (2026.acl-long)
Copied to clipboard
Zihao Tang, Xin Yu, Ziyu Xiao, Zengxuan Wen, Zelin Li, Jiaxi Zhou, Hualei Wang, Haohua Wang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Existing methods for retrieving historical messages are based on similarity-based mechanisms. |
| Approach: | They propose a system that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. |
| Outcome: | The proposed framework achieves state-of-the-art on long-term memory benchmarks and 93.9 on LoCoMo and 91.6 on LongMemEval-S. |
CaTS-Bench: Can Language Models Describe Time Series? (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing time series captioning benchmarks rely on fully synthetic or generic captions . authors propose a pipeline for generating high-fidelity synthetic captions, which is validated . |
| Approach: | They propose a benchmark for Context-aware Time Series reasoning across 11 diverse domains . they evaluate leading Vision-Language Models on their benchmark . |
| Outcome: | The proposed benchmark evaluates 1746 human-rewritten captions and shows they perform better than open-source models. |
Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)
Copied to clipboard
Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu, Sumedha Singla, Brian Vanover, Huijun Qian, Zihao Wang, Fujun Liu, Aashu Singh, Jianyu Wang, Xuewen Zhang
| Challenge: | Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations. |
| Approach: | They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation. |
| Outcome: | The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement. |
COSMIC: Generalized Refusal Direction Identification in LLM Activations (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods depend on predefined refusal templates detectable in output tokens or manual review. |
| Approach: | They propose a framework that optimally identifies steering directions and target layers using cosine similarity, entirely independent of output text. |
| Outcome: | The proposed framework achieves comparable steering effectiveness without any prior knowledge or assumptions of a model’s refusal behavior such as the use of certain refusal tokens. |
Responding E-commerce Product Questions via Exploiting QA Collections and Reviews (C18-1)
Copied to clipboard
| Challenge: | Existing QA and review collections can be used to provide instant responses to product questions . a proposed framework can be applied to a real-world commercial E-commerce site . |
| Approach: | They propose a framework for automatically responding product questions in E-commerce sites . existing QA pairs are exploited as distant supervision for learning to rank responses . |
| Outcome: | The proposed framework can return a ranked list of snippets serving as the automated response for a given question. |
LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data (2024.lrec-main)
Copied to clipboard
| Challenge: | Prior research on Twitter has provided positive evidence of its utility in developing supplementary health surveillance systems. |
| Approach: | They propose a framework to surveil public health, focusing on mental health outcomes by using tweets from 765 neighborhoods in the USA. |
| Outcome: | The proposed framework achieves the highest F1-score and accuracy over the previous framework, and extrapolates CDC’s estimates to proxy unreported neighborhoods. |
Activation-Guided Local Editing for Jailbreaking Attacks (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for jailbreaking Large Language Models (LLMs) are limited and produce incoherent or unreadable inputs. |
| Approach: | They propose a two-stage framework that performs a one-shot, scenario-based generation of context and rephrases the original malicious query to obscure its harmful intent. |
| Outcome: | The proposed framework achieves state-of-the-art Attack Success Rate, with gains of up to 37.74% over the strongest baseline, and excellent transferability to black-box and large-scale models. |