Papers by Zihang Wang

RFS-Guard: Detecting Reasoning Hallucinations via Cross-Phase Routing Focus in Large Reasoning Models (2026.acl-long)

Copied to clipboard

Zihang Liu, Fang Zhouhua, Hui Liu, Zhiwei Liu, Yong Li, Haishuai Wang

Challenge:	Large reasoning models (LRMs) generate intermediate reasoning traces before the final answer, yet they remain vulnerable to reasoning hallucinations such as subtle arithmetic errors.
Approach:	They propose a Routing Focus Score (RFS) that measures how strongly cross-step attention routing aligns with semantic proximity derived from hidden-state cosine similarity.
Outcome:	The proposed framework detects and localizes hallucinations without external tools or repeated sampling.

SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation (D18-1)

Copied to clipboard

Xinyi Wang, Hieu Pham, Zihang Dai, Graham Neubig

Responsible & Trustworthy NLP

Challenge:	Existing methods for data augmentation for text-based tasks such as machine translation are limited due to noise and noise.
Approach:	They propose a data augmentation policy with desirable properties as an optimization problem and propose 'SwitchOut' switchout randomly replaces words in both the source and target sentences with other random words from their corresponding vocabularies.
Outcome:	The proposed method outperforms strong alternatives such as word dropout on three translation datasets.

IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning (2023.findings-acl)

Copied to clipboard

Zihang Xu, Ziqing Yang, Yiming Cui, Shijin Wang

Language Models

Challenge:	Existing systems for logical reasoning have surpassed the average performance of humans in many tasks like SQuAD but there is still a long way to go when it comes to logical reasoning.
Approach:	They propose an InDicator-Oriented Logic Pre-training task which logically strengthens pre-trained models with the help of 6 types of logical indicators and a logicalally rich dataset.
Outcome:	The proposed task achieves state-of-the-art on ReClor and LogiQA, the two most representative benchmarks in logical reasoning MRC.

SciSketch: An Open-source Framework for Automated Schematic Diagram Generation in Scientific Papers (2025.emnlp-demos)

Copied to clipboard

Zihang Wang, Yilun Zhao, Kaiyan Zhang, Chen Zhao, Manasi Patwardhan, Arman Cohan

Multimodality

Challenge:	SCISKETCH is an open-source framework that supports two automated workflows for schematic diagram generation using foundation models.
Approach:	They propose an open-source framework that supports two automated workflows for schematic diagram generation using foundation models.
Outcome:	The open-source framework outperforms several state-of-the-art foundation models in generating schematic diagrams for scientific papers.

CINO: A Chinese Minority Pre-trained Language Model (2022.coling-1)

Copied to clipboard

Ziqing Yang, Zihang Xu, Yiming Cui, Baoxin Wang, Min Lin, Dayong Wu, Zhigang Chen

Multilinguality

Challenge:	Existing multilingual pre-trained language models do not perform well on some low-resource languages.
Approach:	They propose a multilingual pre-trained language model for Chinese minority languages . they collect documents from Wikipedia and construct two classification datasets .
Outcome:	The proposed model outperforms baseline models on various classification tasks.

SciRAG: Adaptive, Citation-Aware, and Outline-Guided Retrieval and Synthesis for Scientific Literature (2026.eacl-long)

Copied to clipboard

Hang Ding, Yilun Zhao, Tiansheng Hu, Zihang Wang, Manasi Patwardhan, Arman Cohan

Information Retrieval

Challenge:	Existing retrieval-augmented generation methods overlook citation graph structure, adapt poorly to complex queries, and yield fragmented, hard-to-verify syntheses.
Approach:	They propose a retrieval-augmented generation framework that addresses these gaps by combining adaptive retrieval and symbolic reasoning.
Outcome:	Extensive experiments show that SciRAG outperforms prior systems in factual accuracy and synthesis quality.

FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks (2022.findings-naacl)

Copied to clipboard

Bill Yuchen Lin, Chaoyang He, Zihang Ze, Hulin Wang, Yufen Hua, Christophe Dupuy, Rahul Gupta, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr

Responsible & Trustworthy NLP

Challenge:	Increasing concerns and regulations about data privacy necessitate the study of privacy-preserving, decentralized learning methods for natural language processing tasks.
Approach:	They propose a framework for evaluating federated learning methods on four different tasks . they propose federation between Transformer-based language models and FL methods .
Outcome:	The proposed framework compares FL methods on four different tasks under non-IID partitioning strategies.

Long-form Hallucination Detection with Self-elicitation (2025.findings-acl)

Copied to clipboard

Zihang Liu, Jiawei Guo, Hao Zhang, Hongyang Chen, Jiajun Bu, Haishuai Wang

Reasoning

Challenge:	Existing methods for hallucination detection tend to decompose text into isolated statements, unable to understand contextual semantics.
Approach:	They propose a framework to leverage self-generated thoughts derived from prior statements as catalysts to elicit the expression of intrinsic knowledge and understand contextual semantics.
Outcome:	The proposed framework enables self-elicitation to elicit expressions of knowledge and understand semantics.

Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation (2026.acl-long)

Copied to clipboard

Jiaying Wu, Zihang Fu, Haonan Wang, Fanxiao Li, Jiafeng Guo, Preslav Nakov, Min-Yen Kan

Reasoning

Challenge:	X (formerly Twitter) users can flag misleading posts, attach contextual notes, and rate the notes’ helpfulness, but there is a significant latency in Community Notes, which is unable to provide accurate notes.
Approach:	They propose a framework that augments Community Notes for faster and more reliable health misinformation governance.
Outcome:	The proposed framework outperforms human contributors in correctness, helpfulness, and evidence utility in health misinformation surges.

Generative Input: Towards Next-Generation Input Methods Paradigm (2024.findings-acl)

Copied to clipboard

Keyu Ding, Yongcan Wang, Zihang Xu, Zhenzhen Jia, Enhong Chen

Language Models

Challenge:	generative models have been used for various NLP tasks but their application in the field of input methods remains under-explored.
Approach:	They propose a novel Generative Input paradigm that uses prompts to handle all input scenarios and other intelligent auxiliary input functions, optimizing the model with user feedback.
Outcome:	The proposed paradigm achieves state-of-the-art in the Full-mode Key-sequence to Characters task and surpasses GPT-4 in the other input methods.