Papers by Wenjie Zhou

15 papers
Cross-Domain Fake News Detection based on Dual-Granularity Adversarial Training (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches to detect fake news in unseen domains are limited by domain-specific training.
Approach: They propose a cross-domain fake news detection method based on adversarial training . they use a document-level and entity-level model to generate domain-independent representations .
Outcome: The proposed method can detect fake news in unseen domains with the help of pre-trained language models.
Don’t Say No: Jailbreaking LLM by Suppressing Refusal (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are vulnerable to "jailbreaking" attacks where crafted prompts manipulate them into producing toxic content.
Approach: They propose to improve the target loss objective by combining a cosine decay schedule method with refusal suppression to achieve higher success rates.
Outcome: The proposed approach outperforms baseline attacks and achieves state-of-the-art attack success rates.
How to Ask Good Questions? Try to Leverage Paraphrases (2020.acl-main)

Copied to clipboard

Challenge: Existing methods to generate human-like questions rely on paraphrases to generate good questions.
Approach: They propose to integrate paraphrase knowledge into question generation to generate human-like questions by combining paraphrases with a back-translation method.
Outcome: The proposed model achieves obvious performance gain over several strong baselines and human evaluation validates that it can ask questions of high quality by leveraging paraphrase knowledge.
A Causal View of Entity Bias in (Large) Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Entity bias affects pretrained (large) language models, causing them to rely on (biased) parametric knowledge to make unfaithful predictions.
Approach: They propose a structured causal model whose parameters are easier to estimate . they propose to perturb the original entity with neighboring entities .
Outcome: The proposed model reduces biasing information pertaining to the original entity while still preserving sufficient semantic information from similar entities.
Revisiting the Self-Consistency Challenges in Multi-Choice Question Formats for Large Language Model Evaluation (2024.lrec-main)

Copied to clipboard

Challenge: Multi-choice questions (MCQs) are a common method for assessing the world knowledge of large language models.
Approach: They propose three knowledge-equivalent question variants to assess LLMs' world knowledge . they propose option position shuffle, option label replacement, and conversion to a True/False format .
Outcome: The proposed questions are shuffle, label replacement, and True/False format.
MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities.
Approach: They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs .
Outcome: The proposed framework improves instruction following performance without compromising general performance.
Multimodal Cross-lingual Phrase Retrieval (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to cross-lingual phrase retrieval only deal with textual modality, leaving the question of the effectiveness of using multimodal information unanswered.
Approach: They propose a multimodal cross-lingual phrase retrieval resource that integrates a Wikimedia Commons media store and a large multimodal pre-trained model to bridge the gap between different modalities.
Outcome: The proposed approach performs significantly better than pure textual cross-lingual phrase retrieval on a benchmarked dataset covering eight language pairs.
Question-type Driven Question Generation (D19-1)

Copied to clipboard

Challenge: Existing work suffers from mismatching between question type and answer . existing work fails to generate questions with type how while answer is personal name .
Approach: They propose to automatically predict the question type based on the input answer and context.
Outcome: The proposed model improves on both SQuAD and MARCO datasets and improves accuracy on the input answer and context.
Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to large language models are limited to historical backtesting and static data.
Approach: a new large-language model is developed to simulate real-time trading in a virtual stock market . the agent trading arena simulates real-world bid-ask interactions and provides real-life trading scenarios .
Outcome: The Agent Trading Arena simulates real-world market conditions and directly impacts price dynamics.
KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing models for multilingual biomedical training are monolingual, resulting in limited cross-lingual capability.
Approach: They propose a model that transforms a multilingual biomedical corpus into a biomedically domain using a knowledge-anchored approach.
Outcome: The proposed model outperforms monolingual and multilingual models in cross-lingual scenarios.
Effective Unsupervised Constrained Text Generation based on Perturbed Masking (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods for constrained text generation stochastically sample edit positions and actions, which cause unnecessary search steps.
Approach: They propose to extend perturbed masking technique to search for most incongruent token to edit and introduce four multi-aspect scoring functions to select edit action to further reduce search difficulty.
Outcome: The proposed method achieves state-of-the-art in two representative tasks . it does not require supervised data, so it could be applied to different generation tasks.
RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems (2026.acl-demo)

Copied to clipboard

Challenge: Recent advances in large language model (LLM) agents have accelerated deployment of multi-agent systems for complex tasks.
Approach: They propose an open-source toolkit for instantiating, probing, and measuring emergent risks in LLM-based multi-agent systems under controlled conditions.
Outcome: The proposed toolkit is based on a structured topology–environment–protocol–agent–task quintuple enabling reproducible studies of how communication structure, coordination mechanisms, and incentives shape system-level risks.
Personality Understanding of Fictional Characters during Book Reading (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to predict characters' personalities have not been studied in the NLP field due to the lack of appropriate datasets mimicking the process of book reading.
Approach: They propose a dataset to predict characters' personalities that uses an exhaustive vocabulary of personality traits as targets.
Outcome: The proposed dataset is efficient and accurate and relies on long-term context to achieve accurate predictions for both machines and humans.
GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillation (2024.emnlp-industry)

Copied to clipboard

Challenge: Pre-trained language models have achieved remarkable performance in OpenQA, but for practical deployment, knowledge distillation is crucial to maintain high performance while operating under computational constraints.
Approach: They propose an algorithm to perform unsupervised knowledge distillation without the guidance of labels to achieve 99.5% of performance.
Outcome: The proposed algorithm achieves 99.5% of performance in a commercial question-answering system.
Multi-Task Learning with Language Modeling for Question Generation (D19-1)

Copied to clipboard

Challenge: Existing work on answer-aware questions generates a sentence and answer span as input . previous work on QG was mainly tackled by rule-based approach and neural-based one .
Approach: They propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical multi-task learning structure.
Outcome: The proposed model improves on SQuAD and MARCO datasets and human evaluation proves it.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations