Papers by Zhengyu Wang
HTML: Hierarchical Topology Multi-task Learning for Semantic Parsing in Knowledge Base Question Answering (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches struggle with mapping questions to precise logical forms . Existing frameworks struggle with complex mapping of questions to logical form . |
| Approach: | They propose a framework that leverages a hierarchical multi-task learning paradigm to enhance the performance of logical form generation. |
| Outcome: | The proposed framework outperforms supervised fine-tuning methods and training-free ones on large language models. |
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing jailbreaking methods generate harmful and unethical content when subjected to jailbreaking attacks. |
| Approach: | They propose a black-box jailbreaking method with optimizable suffixes that translate jailbreaking objectives into natural language instructions. |
| Outcome: | The proposed method outperforms existing methods by 2.4 times in the ASR of three open-source LLMs and GPT-3.5-Turbo. |
Typographic Attacks in a Multi-Image Setting (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Vision-Language Models are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. |
| Approach: | They propose a multi-image setting for studying typographic attacks by leveraging the difficulty of the target image, the strength of the attack text, and text-image similarity. |
| Outcome: | The proposed approach improves success rates by 21% over random, non-specific methods on the CLIP model while maintaining stealth in a multi-image scenario. |
Deep Reinforcement Learning-based Dialogue Policy with Graph Convolutional Q-network (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for deep reinforcement learning lack the ability to learn the relationship between dialogue states and actions. |
| Approach: | They propose a graph-structured dialogue policy framework for task-oriented dialogue systems that uses bipartite graphs to construct two different bipartites and generate user-related and knowledge-related subgraphs. |
| Outcome: | The proposed framework significantly improves the effectiveness and stability of dialogue policies. |
ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing retrieval models rank tools based on similarity between query and tool description (TD) Existing tools are not conditioned to learn tool-to-tool relationships (middle). |
| Approach: | They propose a framework that conditions retrieval models to fetch tools based on hypothetical (synthetic) TD generated using an LLM. |
| Outcome: | The proposed framework improves the performance of sparse and dense retrievers with and without training, showcasing its flexibility. |
DelucionQA: Detecting Hallucinations in Domain-specific Question Answering (2023.findings-emnlp)
Copied to clipboard
Mobashir Sadat, Zhengyu Zhou, Lukas Lange, Jun Araki, Arsalan Gundroo, Bingqing Wang, Rakesh Menon, Md Parvez, Zhe Feng
| Challenge: | Hallucination is a well-known phenomenon in text generated by large language models . state-of-the-art LLMs still have a number of weaknesses, including the tendency to generate hallucinatory statements without considering the factuality . |
| Approach: | They propose a dataset that captures hallucinations made by retrieval-augmented LLMs . they propose to use these methods to help detect hallucinosity in QA tasks . |
| Outcome: | The proposed method captures hallucinations made by retrieval-augmented LLMs for QA tasks. |
Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies (2025.acl-long)
Copied to clipboard
| Challenge: | Existing scaling laws suggest augmenting model size and training data results in enhanced performance, but recent studies reveal deviations, particularly in large language models, where performance improvements decelerate—a phenomenon known as sub-scaling. |
| Approach: | They propose a sub-optimal scaling law that better predicts performance in sub-scaling regimes by examining data quality and training strategies. |
| Outcome: | The proposed scaling law better predicts performance in sub-scaling regimes, highlighting the importance of data quality and diversity. |
Profile Consistency Identification for Open-domain Dialogue Agents (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on improving attribute consistency focus on incorporating attribute information in responses, but few efforts have identified the consistency relations between response and attribute profile. |
| Approach: | They propose a key-value structure information enriched BERT model to identify the profile consistency . they propose to incorporate attribute information into the generated responses . |
| Outcome: | The proposed model improves over strong baselines on downstream tasks. |
Let’s Ask GNN: Empowering Large Language Model for Graph In-Context Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Textual Attributed Graphs (TAGs) are crucial for modeling complex real-world systems, yet leveraging large language models (LLMs) for TAGs presents unique challenges due to the gap between sequential text processing and graph-structured data. |
| Approach: | They propose a novel approach that leverages In-Context Learning to integrate graph data and task-specific information into large language models (LLMs) they employ a Graph Neural Network-powered structure-enhanced retriever to select labeled nodes across graphs, incorporating complex graph structures and their supervision signals. |
| Outcome: | Experiments on three tasks and seven LLMs show that AskGNN performs better than existing methods. |
CoAug: Combining Augmentation of Labels and Labelling Rules (2023.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) tasks require large labeled datasets to perform well. |
| Approach: | They propose a co-augmentation framework that bootstraps predictions from each model to improve few-shot models and rule-augmentation models by bootstrapping them. |
| Outcome: | The proposed model outperforms strong weak-supervision-based models by 6.5 F1 points . the proposed model can learn from limited labeled data and perform better on small datasets . |
Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | a study of large language models (LLMs) reveals the transferability and discrepancies of scaling laws between Dense and MoE models. |
| Approach: | They investigate the transferability and discrepancies of scaling laws between Dense Models and Mixture of Experts models. |
| Outcome: | The results show that the power-law scaling framework also applies to MoE Models . |
SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity (2025.findings-emnlp)
Copied to clipboard
Xiangyu Xi, Deyang Kong, Jian Yang, Jiawei Yang, Zhengyu Chen, Wei Wang, Jingang Wang, Xunliang Cai, Shikun Zhang, Wei Ye
| Challenge: | Existing methods for pretraining data mixing for large language models neglect significant inter-domain overlaps and commonalities, failing to control the global diversity of the constructed training dataset. |
| Approach: | They propose a sample-wise data mixture approach that performs global cross-domain sampling by systematically evaluating the quality and diversity of each sample. |
| Outcome: | The proposed method exceeds existing domain-based methods in multiple downstream tasks and perplexity assessments. |
Explaining Length Bias in LLM-Based Preference Evaluations (2025.findings-emnlp)
Copied to clipboard
Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhengyu Chen, Nicholas Jing Yuan, Jianxun Lian, Kaize Ding, Hui Xiong
| Challenge: | a preference evaluation metric is often biased towards longer responses, revealing a reliability problem . a decomposition of the preference evaluation into two components is needed to understand this bias. |
| Approach: | They propose to decompose the preference evaluation metric into two key components . the first component is length-dependent and related to trustworthiness . |
| Outcome: | The proposed evaluation metric is based on two components: desirability and information mass. |
Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder (2024.acl-long)
Copied to clipboard
| Challenge: | EEG-based language decoding is still in its nascent stages, despite promising applications in brain-computer interfaces. |
| Approach: | They propose a novel EEG-text Masked Autoencoder that orchestrates compound self-supervised learning across and within EEG and text through a dedicated multi-stream encoder. |
| Outcome: | The proposed model outperforms baseline framework in ROUGE-1 F1 and BLEU-4 scores and an LLM (specifically BART) to improve downstream tasks involving EEG and text. |